Abstract: This disclosure includes a method for correcting errors on a DRAM having an ECC which includes writing data to a DRAM row, reading data from the DRAM row, detecting errors in the data that cannot be corrected by the DRAM's ECC, determining erasure information for the row, evaluating the errors using the erasure information, and correcting the errors in the data.

Abstract: This disclosure includes a method for correcting errors on a DRAM having an ECC which includes writing data to a DRAM row, reading data from the DRAM row, detecting errors in the data that cannot be corrected by the DRAM's ECC, determining erasure information for the row, evaluating the errors using the erasure information, and correcting the errors in the data.

Abstract: Marking memory chips as faulty when a fault is detected in data from the memory chip. Upon detecting that a plurality of memory chips are faulty, determining which of a plurality of memory channels contains the faulty memory chips. Marking one of a plurality of memory channels as failing in response to determining that the number of failing memory chips has exceeded a threshold.

Abstract: Channel marking is provided in a memory system that includes a memory channel with a plurality of memory devices. The memory devices are arranged into a first group of memory devices and a second group of memory devices. The memory system is configured to perform a method that includes determining that more than a threshold number of memory devices in the first group are failing. An error correction code (ECC) is configured to compensate for errors associated with memory devices in the first group on the memory channel and to perform error correction on errors associated with memory devices in the second group on the memory channel.

Abstract: A refresh of a DRAM having at least a fast and a slow refresh rate includes encoding a pointer on a row or rows with refresh information, reading the refresh information, and incrementing a fast refresh address counter with the refresh information. The refresh may be performed by encoding one or more cells on a row that may require a fast refresh, one or more cells on a group of rows that may require a fast refresh, or one or more cells on a row that may not require a fast refresh.

Abstract: Embodiments relate to adaptive write leveling in limited lifetime memory devices. A write data stream that includes write line addresses is monitored. A property of the write data stream is detected and a write leveling process is adapted in response to the detected property. The write leveling process is applied to the write data stream to generate physical addresses from the write line addresses.

Abstract: A method for determining an optimized refresh rate involves testing a refresh rate on rows of cells, determining an error rate of the rows, evaluating the error rate of the rows; and repeating these steps for a decreased refresh rate until the error rate is greater than a constraint, at which point a slow refresh rate is set.

Abstract: A method and apparatus for controlling marking store updates in a central electronic complex with a plurality of core processors and eDRAM cache and interconnect bus to a service processor for loading memory controller firmware to dual-channel DDR3 memory controllers with an internal marking store. Loaded firmware of the memory controllers is responsible for tracking of ECC errors using a ECC decoder control whereby said marking store is written by a slow ECC decoder, and read by a fast ECC decoder for every read operation of said memory controllers to provide a blocking mechanism for notifying marking store firmware when the marking store has been updated and which guarantees that marking store firmware cannot write to the marking store until the marking store firmware has seen updates without causing the marking store hardware to time out.

Abstract: In one exemplary embodiment of the invention, a method includes: receiving a first description for a circuit whose operation over a plurality of inputs is to be verified; receiving a second description for expected behavior of the circuit, where the expected behavior in the second description is expressed as a set of algebraic systems of multivariable polynomials over at least one Galois field; applying at least one computational algebraic geometry technique to a combination of the first description and the second description to determine whether the circuit is verified, where verification of the circuit confirms that at least one output obtained based on the first description corresponds to at least one expected value based on the expected behavior expressed in the second description; and outputting an indication as to whether the circuit is verified.

Abstract: Providing heterogeneous recovery in a redundant memory system that includes a memory controller, a plurality of memory channels in communication with the memory controller, an error detection code mechanism configured for detecting a failing memory channel, and an error recovery mechanism. The error recovery mechanism is configured for receiving notification of the failing memory channel, for performing a recovery operation on the failing memory channel while other memory channels are performing normal system operations, for bringing the recovered channel back into operational mode with the other memory channels for store operations, for continuing to mark the recovered channel to guard against stale data, for removing any stale data after the recovery operation is complete, and for removing the mark on the recovered channel to allow the normal system operations with all of the memory channels, the removing in response to the removing any stale data being complete.

Abstract: Correction of structured burst errors in data is provided by a system that includes an encoder and is configured for performing a method. The method includes receiving data that includes a plurality of subsets of data. The data is encoded by an encoder using a combination of a first error correcting code and a second error correcting code. The first error correcting code is configured to provide error recovery from a structured burst error in one of the subsets of data, the structured burst error having a length less than a specified maximum length. The second error correcting code is configured to extend the first error correcting code to provide error recovery from the structured burst error in any of the subsets of data. The encoded data is output.

Abstract: Techniques are presented that include determining, for data to be written to a nonvolatile memory, a location in the nonvolatile memory to which the data should be written based at least on one or more wear metrics corresponding to the location. The one or more wear metrics are based on measurements of the location. The measurements estimate physical wear of the location. The techniques further include writing the data to the determined location in the nonvolatile memory. The techniques may be performed by methods, apparatus (e.g., a memory controller), and computer program products.

Abstract: Techniques are presented that include determining, for data to be written to a nonvolatile memory, a location in the nonvolatile memory to which the data should be written based at least on one or more wear metrics corresponding to the location. The one or more wear metrics are based on measurements of the location. The measurements estimate physical wear of the location. The techniques further include writing the data to the determined location in the nonvolatile memory. The techniques may be performed by methods, apparatus (e.g., a memory controller), and computer program products.

Abstract: A data protection method is provided that includes determining a compressibility score of one or more lines of data stored in a memory. The memory includes a first area characterized by a first reliability level and a second area characterized by a second reliability level. Lines of data with a first compressibility score are migrated to the first area of the memory. Lines of data with a second compressibility score are migrated to the second area of the memory.

Abstract: An embodiment is a method for encoding data with an error correction code. The method includes receiving a first number of data symbols by a memory controller, receiving a second number of meta-data sub-symbols, generating a third number of check symbols using an ECC, where the third number includes a difference between a number of symbols in an ECC codeword and the first number and generating a mismatch vector from the check and meta-data sub-symbols, where a number of sub-symbols of the mismatch vector includes the second number. The method also includes generating an adjustment syndrome symbol by multiplying the mismatch vector by a matrix, generating the third number of adjusted check symbols responsive to the adjustment syndrome symbol, and generating a final codeword by concatenating the adjusted check symbols and the data symbols, where the final codeword includes the number of symbols in the ECC codeword.

Abstract: Failing bus lane detection using syndrome analysis, including a method for receiving a plurality of syndromes of an error detection code, the error detection code associated with a plurality of frames that have been transmitted on a bus that includes a plurality of lanes and is protected by the error detection code. The method includes performing for each of the lanes in each of the syndromes: decoding the syndrome under an assumption that the lane is a failing lane, the decoding outputting a decode result; determining if the decode result is a valid decode; and voting for the lane in response to determining that the decode result is a valid decode. A failing lane is then identified in response to the voting, with the failing lane being characterized by having more votes than at least one other lane on the bus.

Abstract: Providing increased capacity in heterogeneous storage elements including a method for storing data in a heterogeneous memory that includes receiving a write message and a write address corresponding to a block of memory cells where at least two of the memory cells support different data levels, determining physical characteristics of the memory cells, and identifying virtual memories associated with the block of memory cells in response to the physical characteristics. The following is performed for each of the virtual memories: generating a constraint vector that describes the virtual cells in the virtual memory; and calculating a virtual write vector in response to the constraint vector and the write data, the calculating including writing the write data, bit by bit, in order, into the virtual memory, skipping locations known to be stuck to a particular value as indicated by the constraint vector.

Abstract: Error correction and detection in a redundant memory system including a a computer implemented method that includes receiving data including error correction code (ECC) bits, the receiving from a plurality of channels, each channel comprising a plurality of memory devices at memory device locations. The method also includes computing syndromes of the data; receiving a channel identifier of one of the channels; and removing a contribution of data received on the channel from the computed syndromes, the removing resulting in channel adjusted syndromes. The channel adjusted syndromes are decoded resulting in channel adjusted memory device locations of failing memory devices, the channel adjusted memory device locations corresponding to memory device locations.

Abstract: Correcting memory device (chip) and memory channel failures in the presence of known memory device failures. A memory channel failure is located and corrected, or alternatively up to c chip failures are corrected and up to d chip failures are detected in the presence of up to u chips that are marked as suspect. A first stage of decoding is performed that results in recovering an estimate of correctable errors affecting the data or in declaring an uncorrectable error state. When an uncorrectable error state is declared, a second stage of decoding is performed to attempt to correct u erasures and a channel error in M iterations where the channel location is changed in each iteration. A correctable error is declared in response to exactly one of the M iterations being successful.

Abstract: Discarded memory devices unfit for an original purpose can be reclaimed for reuse for another purpose. The discarded memory devices are tested and evaluated to determine the level of performance degradation therein. A set of an alternate usage and an information encoding scheme to facilitate a reuse of the tested memory device is identified based on the evaluation of the discarded memory device. A memory chip controller may be configured to facilitate usage of reclaimed memory devices by enabling a plurality of encoding schemes therein. Further, a memory device can be configured to facilitate diagnosis of the functionality, and to facilitate usage as a discarded memory unit. Waste due to discarded memory devices can be thereby reduced.