Abstract: A method is provided for determining log-likelihood ratio (LLR) for soft decoding based on information obtained from hard decoding, in a storage system configured to perform hard decoding and soft decoding of low-density parity-check (LDPC) codewords. The method includes performing hard decoding of codewords in a page, the hard decoding including a first hard read and one or more re-reads using predetermined hard read threshold voltages, and grouping memory cells in the page into a plurality of bins based on the read threshold voltages for the first hard read and the one or more re-reads. The method also includes computing parity checksum and one's count for memory cells in each bin, and determining LLR for each bin of memory cells based on read data, checksums, and one's count for each bin.

Abstract: A controller determines whether or not a read threshold voltage, other than a history read threshold voltage being a read threshold voltage that was used in previously successful read operation, is to be used for a next read operation, based on a fail bit count associated with the read operation, an error correction capability of a decoder and utilization of a queue in the decoder. When it is determined that the history read threshold voltage is not to be used for the next read operation, the controller determines fail bit counts associated with read operations on memory cells of a memory device using read threshold voltages. The controller determines an optimal read threshold voltage based on the fail bit counts. The controller transmits, to the memory device, a first command including a parameter associated with setting the optimal read threshold voltage.

Abstract: Techniques related to improving the decoding performance of codewords, such as LDPC codewords, are described. In an example, the error-correction capability of a decoding layer is improved, where the improvements may include lowering the error floor. To do so, higher order information is used in the decoding. Higher order information refers to, during the decoding of a variable node that is in error, using information that is not limited to the variable node and check nodes connected thereto, but includes information related to variable nodes that are also in error and connected to the variable node via satisfied check nodes and related to unsatisfied check nodes connected to such variable nodes.

Abstract: Devices, systems and methods for improving the performance of a memory device are described. An example method includes obtaining a plurality of cell counts for each of a plurality of read voltages applied to the memory device, generating, based on the plurality of cell counts and the plurality of read voltages, at least one ones count, at least one checksum, and a plurality of samples corresponding to a distribution function of at least one read voltage of the plurality of read voltages, determining an updated value for the at least one read voltage based on an output of a deep neural network whose input comprises the at least one ones count, the at least one checksum, and the plurality of samples, and applying the updated value of the at least one read voltage to the memory device to retrieve information from the memory device.

Abstract: A memory system includes a memory device and a controller. The controller determines a target word line group to which a target word line corresponding to a read command belongs. The controller identifies a reference voltage corresponding to the target word line group. The controller controls the memory device to perform a read operation on a target page coupled to the target word line, using the reference voltage.

Abstract: Devices, systems, and methods for detecting and mitigating oscillations in a bit-flipping decoder associated with a non-volatile memory are described. An example method includes receiving a noisy codeword based on a transmitted codeword generated from a low-density parity-check code, performing a first plurality of decoding iterations on the noisy codeword, which comprises performing a message passing algorithm in a first order, computing, based on a completion of the first plurality of decoding iterations, a plurality of checksum values and a plurality of bit flip counts corresponding to the first plurality of decoding iterations, determining that the plurality of checksum values and the plurality of bit flip counts are periodic with a period less than a predetermined threshold, and performing a subsequent decoding iteration on the noisy codeword, the subsequent decoding iteration comprising performing the message passing algorithm in a second order different from the first order.

Abstract: Techniques related to methods and systems for improving a performance related to reading data stored in memory cells. The method includes selecting a first voltage read range and a second voltage read range from multiple voltage read ranges that are associated with a number of bits storable in a memory cell. The method includes receiving, a first set of parameters that represent a first probability distribution of first candidate voltage read thresholds within the first voltage read range. The method includes receiving a second set of parameters that represent a second probability distribution of second candidate voltage read thresholds within the second voltage read range. The method includes generating, based on an input to an objective function, a voltage read threshold. The method includes reading data stored in the memory cell based on the voltage read threshold.

Abstract: A controller determines whether or not a read threshold voltage, other than a history read threshold voltage being a read threshold voltage that was used in previously successful read operation, is to be used for a next read operation, based on a fail bit count associated with the read operation, an error correction capability of a decoder and utilization of a queue in the decoder. When it is determined that the history read threshold voltage is not to be used for the next read operation, the controller determines fail bit counts associated with read operations on memory cells of a memory device using read threshold voltages. The controller determines an optimal read threshold voltage based on the fail bit counts. The controller transmits, to the memory device, a first command including a parameter associated with setting the optimal read threshold voltage.

Abstract: Embodiments adaptively determine a read retry threshold voltage for a next read operation using meta information collected from previous failed read data. A controller obtains meta information associated with a read operation on a select page, the meta information including a read threshold voltage set. The controller determines a mathematical model for estimating a checksum value for data associated with a next read operation, using a set function of the read threshold voltage set and a set checksum value. The controller determines a set of parameters by performing polynomial regression on the mathematical model. The controller estimates a next read threshold voltage for the next read operation based on the set of parameters.

Abstract: Embodiments adaptively determine a read retry threshold voltage for a next read operation using meta information collected from previous failed read data. A controller obtains meta information associated with a read operation on a select page, the meta information including a read threshold voltage set. The controller determines a mathematical model for estimating a checksum value for data associated with a next read operation, using a set function of the read threshold voltage set and a set checksum value. The controller determines a set of parameters by performing polynomial regression on the mathematical model. The controller estimates a next read threshold voltage for the next read operation based on the set of parameters.

Abstract: A controller optimizes a read threshold value for a memory device using model-less regression. The controller performs read operations on cells using read threshold voltage values. The controller measures probability values for the multiple read threshold voltage values, and estimates a threshold voltage distribution curve based on the multiple read threshold voltage values and the measured probability values using a set regression formula. The controller determines a read threshold voltage value corresponding to a set point on the threshold voltage distribution curve, and performs a read operation on the cells using the read threshold voltage value.

Abstract: Techniques related to a low-power, low-memory multiply and accumulate (MAC) unit are described. In an example, the MAC unit performs a MAC operation that represents a multiplication of numbers. At least the bit representation of one number is compressed based on a quantization and a clustering of quantization values, whereby index bits are used instead of the actual bit representation. The index bits are loaded in an index buffer and a bit representation of another number is loaded in an input buffer. The index bits are used in a lookup to determine whether the corresponding bit representation and shift operations are applied to the input buffer based on this bit representation, followed by accumulation operations.

Abstract: Techniques are described for memory writes and reads according to a chip-kill scheme that allows recovery of multiple failed wordlines. In an example, when reading data from a superblock of the memory, where the decoding of multiple wordlines failed, a computer system schedules the decoding of failed wordlines based on quantity of bit errors and updates soft information based on convergence or divergence of the scheduled decoding. Such a computer system significantly reduces decoding failures associated with data reads from the memory and allows improved data retention in the memory.

Abstract: Devices, systems and methods for improving the performance of a memory device are described. An example method includes obtaining a plurality of cell counts for each of a plurality of read voltages applied to the memory device, generating, based on the plurality of cell counts, a set of Gaussian models for a plurality of PV states corresponding to the plurality of read voltages, each of the set of Gaussian models comprising a mean parameter and a standard deviation parameter, determining, based on the set of Gaussian models, the mean parameter and the standard deviation parameter for each of the plurality of PV states, determining, based on the mean parameter and the standard deviation parameter for each of the plurality of PV states, a plurality of updated read voltages, and applying the plurality of updated read voltages to the memory device to retrieve information from the memory device.

Abstract: A controller optimizes a read threshold value for a memory device using model-less regression. The controller performs read operations on cells using read threshold voltage values. The controller measures probability values for the multiple read threshold voltage values, and estimates a threshold voltage distribution curve based on the multiple read threshold voltage values and the measured probability values using a set regression formula. The controller determines a read threshold voltage value corresponding to a set point on the threshold voltage distribution curve, and performs a read operation on the cells using the read threshold voltage value.

Abstract: Devices, systems and methods for improving decoding operations of a decoder are described. An example method includes receiving a noisy codeword that is based on a transmitted codeword generated from a low-density parity-check (LDPC) code, the LDPC code having an associated parity matrix comprising N columns, wherein each of at least B columns of the parity matrix has a column weight that exceeds a predetermined column weight, processing the N columns based on a message passing algorithm, and determining, based on the processing, a candidate version of the transmitted codeword, wherein the processing for each of the N columns comprises performing a read operation, a variable node update (VNU) operation, and a check node update (CNU) operation on the first set and the second set, the read operation and the CNU operation on each of the at least B columns spanning two or more time-steps.

Abstract: A controller optimizes read retry thresholds for a memory device using one or more previous reads and a condition. The controller determines a read level table based on a condition indicative of a state of the memory device and selects an entry among multiple entries in the selected read level table based on a historical read threshold. For the selected entry, the controller: determines fail bits for data associated with multiple read operations on the cells using multiple read retry thresholds; and determines an order of the multiple read retry thresholds based on the fail bits determination.

Abstract: A control of a memory system includes firmware and one error correction code (ECC) module. The module includes a power control engine and ECC components, each ECC component including a power monitor and a power controller. The firmware configures a window of time and a power consumption rate of a select ECC component depending on characteristics of the memory system. The power monitor of the select ECC component measures a power consumption of the select ECC component within the window. The power control engine receives the measurement of power consumption, decides a next power level for the select ECC component, and controls the power controller of the select ECC component such that the select ECC component operates at the next power level.

Abstract: Techniques related to improving power consumption of an LDPC decoder are described. In an example, the LDPC decoder uses a message passing algorithm between variable nodes and check nodes. A check node processing unit that generates check node to variable node messages implements a plurality of check node processing mode. Operation in each mode consumes a certain amount of power while providing a certain accuracy. Depending on a reliability of a variable node to check node message received by the check node processing unit, an appropriate check node processing mode is selected and used to generate a corresponding check node to variable node message. The reliability can be estimated for a set of variable node to check node messages based on, for instance, syndrome-related parameters.

Abstract: Techniques related to methods and systems for improving a performance related to reading data stored in memory cells. The method includes selecting a first voltage read range and a second voltage read range from multiple voltage read ranges that are associated with a number of bits storable in a memory cell. The method includes receiving, a first set of parameters that represent a first probability distribution of first candidate voltage read thresholds within the first voltage read range. The method includes receiving a second set of parameters that represent a second probability distribution of second candidate voltage read thresholds within the second voltage read range. The method includes generating, based on an input to an objective function, a voltage read threshold. The method includes reading data stored in the memory cell based on the voltage read threshold.