Hewlett-packard Development Company, L.p.

Hewlett-packard Company

Avago Technologies General IP (singapore) Pte. Ltd.

Hewlett Packard Enterprise Development LP

Avago Technologies Enterprise IP (singapore) Pte. Ltd.

Larry Jay Thayer

Andrew Christopher Walton

Michael Kennard Tayler

Mike H Cogdill

Roland M Hochmuth

Eric M Rentschler

Samuel C Sands

Dheemanth Nagaraj

Gayani N K Gamage

Byron Alan Alcorn

Mark Edward Shaw

Lidia Warnes

Leith L Johnson

Ronald D Larson

Charles R Dowdell

Mark D Coleman

David Marshall

Philip L Barnes

George Krejci

Leon Sigal

Chris Petersen

A disclosed example bit error rate reduction buffer comprises a data recovery circuit including differential bit pair inputs and differential bit pair outputs, a CRC circuit including differential bit pair inputs, differential bit pair outputs and a fault-isolation indicator, and a serializer including differential bit pair inputs and differential bit pair outputs. The differential bit pair outputs of the data recovery circuit being coupled to the differential bit pair inputs of the CRC circuit, the differential bit pair outputs of the CRC circuit being coupled to the differential bit pair inputs of the serializer, the differential bit pair inputs of the data recovery circuit to be driven by a first HSS link, the different bit pair outputs of the serializer to drive a second HSS link; and the fault-isolation indicator of the CRC circuit to indicate a fault when a fault is detected by the CRC circuit.

Bit error rate reduction buffer, method and apparatus

A memory system is provided in which at least one memory chip and a memory controller chip are mounted in a side-by-side relationship on an interposer. The memory chip is connected to the interposer via a Wide I/O interface to enable the memory chip and the memory controller chip to communicate with each other via the Wide I/O interface. The memory controller chip has an interface for communicating with an interface of an integrated circuit (IC) chip of the memory system.

Memory system that utilizes a wide input/output (I/O) interface to interface memory storage with an interposer

A method and system for repairing high speed serial links is provided. The system includes a first electronic components, connected to at least a second electronic component via at least one link. At least one of the first or second electronic components has a link controller. The link controller is configured to repair serial links by detecting a link error and mapping out individual lanes of a link where the link error is detected. The link controller resumes operation, i.e., transmission of data and continues to monitor the lanes for errors. If and when additional link errors occur, the link controller identifies the lanes in which the link error occurs and deactivates those lanes. The deactivated lane(s) can not be used in further transmissions which, in turn, reduces the occurrence of intermittent link errors.

Repairing high-speed serial links

A memory module including memory devices, a spare memory device, a multiplexing unit, and a memory buffer is provided. The multiplexing unit is coupled with each of the memory devices and the spare memory device, while the memory buffer is coupled with the multiplexing unit. The memory buffer includes a serial interface over which commands are received from a memory controller. The memory buffer is configured to process the commands and provide the memory controller access to the memory device through the multiplexing unit in response to the commands. Also, in response to at least one of the commands, the memory buffer is configured to direct the multiplexing unit to couple the spare memory device to the memory buffer in place of one of the memory devices for at least a next access of the memory devices.

Memory module and method employing a multiplexer to replace a memory device

A memory system is provided in which at least one DRAM chip and a memory controller chip are mounted in a side-by-side relationship on an interposer. The DRAM chip is connected to the interposer via a Wide I/O interface to enable the DRAM chip and the memory controller chip to communicate with each other via the Wide I/O interface. The memory controller chip has a SerDes interface for communicating with a SerDes interface of an integrated circuit (IC) chip of the memory system.

Memory system that utilizes a wide input/output (I/O) interface to interface memory storage with an interposer and that utilizes a SerDes interface to interface a memory controller with an integrated circuit, and a method

System and methods of selectively managing errors in memory modules. In an exemplary implementation, a method may include monitoring for persistent errors in the memory modules. The methods may also include mapping at least a portion of the memory modules to a spare memory cache only to obviate persistent errors. The method may also include initiating memory erasure on at least a portion of the memory modules only if insufficient cache lines are available in the spare memory cache.

Systems and methods of selectively managing errors in memory modules

An interface for a dynamic random access memory (DRAM) includes an interface element coupled to a DRAM chip using a first attachment structure, a first portion of the first attachment structure being used to form a wide bandwidth, low speed, parallel interface, a second portion of the first attachment structure, a routing element and a through silicon via (TSV) associated with the DRAM chip being used to form a narrow bandwidth, high speed, serial interface, the interface element configured to convert parallel information to serial information and configured to convert serial information to parallel information.

High speed interface for dynamic random access memory (DRAM)

A method comprises detecting a defective area in a Dynamic Random Access Memory (DRAM). The method further comprises establishing a redundant memory buffer at a per-memory module level. The method still further comprises loading the redundant memory buffer with a copy of data from the defective area. The method additionally comprises substituting data from the redundant memory buffer for data stored in the defective area upon a memory access to the defective area.

Redundant memory to mask DRAM failures

In one embodiment, a memory control system is provided with a memory controller having 1) a first interface to receive memory read/write requests; 2) a second interface to read/write data from a number of memory modules; 3) a memory cache containing spare memory locations; and 4) logic to, upon receipt of a memory read/write request, i) direct the read/write request to the memory cache when an address associated with the read/write request resides in the memory cache, and ii) direct the read/write request to the second interface when the address associated with the read/write request does not reside in the memory cache.

Memory controller

Systems and methods for distribution analysis of a stacked-die integrated circuit (IC) are described. The stacked-die integrated circuit includes a primary die, and clock load information for the primary die of the IC is determined. Additionally, a clock load model may be created using the clock load information for the primary die. Clock load information for a second die that is coupled to the primary die may also be determined. The clock load information for the second die may be incorporated into the clock load model to create an enhanced clock load model of the stacked-die IC, which may then be analyzed as if a single-die IC.

System and method for distribution analysis of stacked-die integrated circuits

A method is provided for managing defects in a semiconductor memory system having a plurality of addressable locations. In the method, a first plurality of the addressable locations is allocated as in-use locations, and a second plurality of the addressable locations is allocated as spare locations. A plurality of sets of the in-use locations, wherein each of the sets is associated with a memory defect, is determined. At least one of the sets includes a different number of in-use locations than another of the sets. Each of the sets of the in-use locations is associated with at least one corresponding set of the spare locations. Each of a plurality of data requests that is associated with one of the sets of the in-use locations is directed to the at least one corresponding set of the spare locations.

Defect management for a semiconductor memory system

A method is provided for implementing at least one of a number of error correction algorithms operable on a memory. In the method, each of the error correction algorithms is provided. At least one of the error correction algorithms is then selected based on the organization of the memory. At least one error in the memory is corrected using the selected error correction algorithm.

Error correction algorithm selection based upon memory organization

Systems and methods for implementing a stride value for memory are provided. One embodiment relates to a system that includes a plurality of memory modules configured to store interleaved data in a plurality of memory storage units according to a predetermined interleave. A memory test device is configured to perform a memory test that accesses a portion of the plurality of memory storage units in a sequence according to a programmable stride value. The memory test device performs the memory test by writing test data to each of the memory storage units in the portion of the plurality of memory storage units and reading the test data from each of the memory storage units in the portion of the plurality of memory storage units.

System and method for implementing a stride value for memory testing

In a preferred embodiment, the invention provides a circuit for reducing bit error rates. A data recovery circuit recovers data from a first HSS link to differential bit pair inputs. Data from the differential bit pair outputs of the data recovery circuit drive differential bit pair inputs to a plurality of FIFOs. The data is then driven from a parallel output of the plurality of FIFOs to the parallel input of a synchronizer. The data is then driven from the parallel output of the synchronizer to the parallel input of a serializer. The serializer, through different bit pair outputs, drives a second serial HSS link.

Bit error rate reduction buffer

Systems and methods for implementing a stride value for memory are provided. One embodiment includes a system comprising a plurality of memory modules configured to store interleaved data in a plurality of memory storage units according to a predetermined interleave. The plurality of memory storage units can be defined by a memory range of consecutive addresses. The system also comprises a memory test device configured to access a portion of the plurality of memory storage units in a sequence that repeats according to a programmable stride value.

Growing community of inventors

Fort Collins, CO, United States of America

Larry Jay Thayer