Kioxia Corporation

Intel Corporation

Toshiba Memory Corporation

Ofir Kanter

Avi Steiner

Hanan Weingarten

Amir Nassie

Yasuhiko Kurosawa

Eran Peleg

Meir Nadam-Olegnowicz

Anat Rot

Ehud Udi Shoor

Eli Sterin

Yesayahu Levy

Nimrod Bregman

Zion Nahisi

Assaf Sella

Example implementations include a method of optimizing irregular error correction code components in memory devices, a method including obtaining one or more code rate parameters including a payload size parameter, a group size parameter, and a redundancy parameter generating a first number of first code component blocks associated with a first error correction capability, and a second number of code component blocks associated with a second error correction capability aligning the first code component blocks and the second code component blocks to the group size parameter aligning the first code component blocks and the second code component blocks to a code component length constraint, and generating, in accordance with an optimization metric based on the first error correction capability and the second error correction capability, first optimized code components based on the first code component blocks and second optimized code components based on the second code component blocks.

Method and system for error correction in memory devices using irregular error correction code components

Disclosed herein are related to a system and a method for adjusting a read voltage threshold to read data from a plurality of memory dies of a nonvolatile memory device. Each of the plurality of memory dies comprises a plurality of blocks. A controller in communication with the plurality of memory dies may read, from a first block of the plurality of blocks, data corresponding to a read command received from a host. The controller may determine a bit error rate for the first block based on the data. The controller may update the read voltage threshold for the first block when the bit error rate for the first block exceeds a first error threshold. The read voltage threshold may be stored in the controller.

Tracking and updating read command voltage thresholds in solid-state drives

Various implementations described herein relate to systems and methods for decoding data stored in a non-volatile storage device, including determining error candidates and determining whether at least one first error candidate from the error candidates is found based on two of the component codes agreeing on a same error candidate. In addition, whether at least one second error candidate is found based on two of the component codes agreeing on a same error candidate is determined in response to implementing a suggested correction at one of the error candidates. Errors in the data are corrected based on at least one of whether the at least one first error candidate is found or whether the at least one second error candidate is found.

Hard decoding methods in data storage devices

Aspects can include selecting memory locations at a memory device, the memory locations corresponding to a first page including a first plurality of bits and a second plurality of pages including corresponding second pluralities of bits, obtaining, based on the second pluralities of bits, extrinsic page information for a proposed error solution including a third plurality of bits indicating a reliability of respective bits of the first plurality of bits, and rejecting, in response to a determination that the proposed error solution indicates a modification to a reliable bit among the first plurality of bits, the proposed error solution to eliminate a false correction of the first plurality of bits.

Efficient hard decoding of error correction code via extrinsic bit information

Various implementations described herein relate to systems and methods for detecting soft errors, including but not limited to, errors introduced after reading a codeword from a non-volatile memory, and before providing data to a host. Embodiments can include generating the codeword from the non-volatile memory to obtain at least input data, and determining validity of the input data using a first signature after processing the input data through a data path. If it is determined that the input data is valid using the first signature, the input data is sent to a host.

Soft error detection and correction for data storage devices

Systems, methods, non-transitory computer-readable media configured to perform operations associated with a storage medium. One system includes the storage medium and an encoding/decoding (ED) system, the ED system being configured to receive a set of input log-likelihood ratios (LLRs) of a component of the plurality of components, determine an extrinsic estimation function based on a set of features of the set of input LLRs, analyze the extrinsic estimation function to obtain a plurality of extrinsic LLR values, map the plurality of extrinsic LLR values to an input LLR of the set of input LLRs, and output, for each component, a plurality of updated LLR values based on the mapping.

Deep neural network implementation for concatenated codes

Aspects of this technical solution can include selecting a plurality of memory locations at a memory device, the memory locations corresponding to a first page including a first plurality of bits and a second page including a second plurality of bits, modifying, based on the first plurality of bits and the second plurality of bits, a first voltage threshold corresponding to an estimated read voltage for the first plurality of bits, allocating, to a voltage range bounded by the first voltage threshold, a log-likelihood ratio (LLR), and decoding, based on the LLR corresponding to the voltage range, the first plurality of bits.

Efficient soft decoding of error correction code via extrinsic bit information

A system for decoding data stored in a non-volatile storage device may include processing circuits configured to decode, in a first iteration, each of a plurality of component codes corresponding to the data by performing a first number of enumerations over hypotheses. The processing circuits may be configured to determine, in the first iteration, an extrinsic value output for each of the component codes based on log-likelihood ratios (LLRs) of one or more error bits of a codeword. The processing circuits may be configured to determine a second number of enumerations based on the extrinsic value. The processing circuits may be configured to decode, in a second iteration, each of the plurality of component codes by performing the second number of enumerations over hypotheses.

Efficient decoding schemes for error correcting codes for memory devices

Systems, methods, non-transitory computer-readable media to perform operations associated with the storage medium. One system includes a storage medium and an encoding/decoding (ED) system to perform operations associated with the storage medium, the ED system being configured to process a set of log-likelihood ratios (LLRs) and a syndrome vector to obtain a set of confidence values for each bit of a codeword, estimate an error vector based on selecting one or more bit locations with confidence values from the set of confidence values above threshold value and applying hard decision decoding to the selected one or more bit locations, calculate a sum LLR score for the estimated error vector, and output a decoded codeword based on the estimated error vector and the sum LLR score.

Deep neural network implementation for soft decoding of BCH code

A method, of decoding error correction code of a memory device with dynamic bit error estimation, can include generating at least one metric corresponding to one or more syndromes associated with a code word, the code word comprising an error correction code of a memory device, decoding the code word by a first decoder integrated with the memory device, in response to a determination that the metric satisfies a threshold associated with the syndromes, the first decoder having a first execution property, and decoding the code word by a second decoder integrated with the memory device, in response to a determination that the metric does not satisfy the threshold associated with the syndromes, the second decoder having a second execution property distinct from the first execution property, or in response to a determination that the metric satisfies the threshold associated with the syndromes, and in response to a determination to perform further decoding.

Systems and methods of decoding error correction code of a memory device with dynamic bit error estimation

A flash memory system may include a flash memory and a circuit for performing operations on the flash memory. The circuit may be configured to obtain reference voltages from one or more read samples, and a plurality of sets of reference voltages. The circuit may be configured to obtain a plurality of distances, each being a distance between a point corresponding to the obtained reference voltages and a point corresponding to a respective set of reference voltages. The circuit may be configured to determine a first set of reference voltages such that a distance between the point corresponding to the obtained reference voltages and a point corresponding to the first set of reference voltage is a minimum distance of the plurality of distances. The circuit may be configured to perform read operations on locations of the flash memory with the first set of reference voltages.

Clustering for read thresholds history table compression in NAND storage systems

Various implementations described herein relate to systems and methods for performing error correction in a flash memory device by determining suggested corrections by decoding a codeword. In addition, whether a first set of the suggested corrections obtained based on a first component code of the plurality of component codes agree with a second set of the suggested corrections obtained based on a second component code of the plurality of component codes is determined. One of accepting the first set of the suggested corrections or rejecting the first set of the suggested corrections is selected based on whether the first set of the suggested corrections and the second set of the suggested corrections agree.

Decoding scheme for error correction code structure

Various implementations described herein relate to systems and methods for detecting soft errors, including but not limited to, errors introduced after reading a codeword from a non-volatile memory, and before providing data to a host. Embodiments can include decoding the codeword from the non-volatile memory to obtain at least input data, and determining validity of the input data using a first signature after processing the input data through a data path. If it is determined that the input data is valid using the first signature, the input data is sent to a host.

A flash memory system may include a flash memory and a circuit for decoding a result of a read operation on the flash memory using a first codeword. The circuit may be configured to generate an estimated codeword based on a result of hard decoding the first codeword and a result of hard decoding a second codeword. The circuit may be further configured to generate soft information based on the hard decoding result of the first codeword and the estimated codeword. The circuit may be further configured to decode the result of the read operation on the flash memory using the soft information.

Growing community of inventors

Haifa, Israel

Ofir Kanter