Lsi Corporation

Skhynix Inc.

Broadcom Corporation

Avago Technologies General IP (Singapore) Pte. Ltd.

Seagate Technology Incorporated

Agere Systems Inc.

Sk Hynix Memory Solutions Inc.

Johnson Yen

Lei Chen

Erich Franz Haratsch

Victor A Krachkovsky

Andrei Vityaev

Milos Ivkovic

Shaohua Yang

Aman Bhatia

Yi-Min Lin

Naveen Kumar

Nenad Miladinovic

Clifton James Williamson

Zongwang Li

Chung-Li Wang

Harley F Burger, Jr

Ngok Ying Chu

Wei-Hao Yuan

Abhiram Prabhakar

Madhusudan Kalluri

Herjen Wang

Fan Zhang

Haitao Xia

Bruce Alexander Wilson

Lingqi Zeng

Nils Graef

Jefferson E Singleton

Sancar Kunt Olcay

Ngok Ning Chu

Ba-Zhong Shen

Jason Bellorado

Kiran Kumar Gunnam

Yu Cai

Ming Jin

Tak Kwan Lee

Yi-Hsien Hao

Hong Lu

Jianqing Chen

Jing Lu

Chun Hok Ho

Michael Veng-Chong Lau

Gong Luo

HongChich Chou

Nirav P Dave

Sathiyanarayanan Sampath Kumar

Chu N Ying

ChunHok Ho

Clifton Williamson

A memory system with a shared buffer architecture for multiple decoders reduces transfer latency and power consumption. Such memory system includes a memory device to generate codewords, and a dynamic memory access (DMA) assembly to receive the generated codewords. A first decoding stage of the system comprises a checksum module and a shared memory buffer, including a memory manager and destination ports, that stores and manages codewords received from the DMA assembly. A second decoding stage of the system comprises a bit-flipping (BF) decoder and a min-sum (MS) decoder, each in communication with the shared memory buffer through a respective one of the destination ports. In managing the codewords stored in the shared memory buffer, the memory manager controls assignment including reassignment of the codewords among the destination ports.

Memory system with shared buffer architecture for multiple decoders and method of operating such memory system

A memory device can include a memory array, a processor coupled to the memory array, and a decoding apparatus. The decoding apparatus is configured to perform parallel decoding of codewords. Each of the codewords has a plurality of data blocks, each data block having a number of data bits. The decoding apparatus is configured to decode in parallel two or more codewords, which share a common data block, to determine error information associated with each codeword. For each error, the error information identifies a data block having the and associated error bit patterns. The decoding apparatus is configured to update the two or more codewords based on the identified data blocks having errors and the associated error bit patterns.

Data dependency mitigation in parallel decoders for flash storage

A memory device can include a memory array, a processor coupled to the memory array, and a decoding apparatus. The decoding apparatus is configured to perform parallel decoding of codewords. Each of the codewords has a plurality of data blocks, and each data block having a number of data bits. The decoding apparatus is configured to decode, in parallel, a first codeword with one or more other codewords to determine error information associated with each codeword. For errors in a common data block shared between two codewords being decoded in parallel, the error information includes a data block identifier and associated error bit patterns. Further, the decoding apparatus is configured to update the codewords based on the error information.

System and method for parallel decoding of codewords sharing common data

Efficient data path architecture for flash devices requiring multi-pass programming utilizes an external memory as an intermediate buffer to store the encoded data used for a first pass programming of the flash device. The stored encoded data can be read from the external memory for subsequent passes programming instead of fetching the data from an on-chip memory, which stores the data received from a host system. Thus, the on-chip memory can be made available to speed up the next data transfer from the host system.

Efficient data path architecture for flash devices configured to perform multi-pass programming

A first memory location stores circulant contents of portions A, C, E, and B of a parity check matrix H. A second memory location stores circulant column counts of the portions A, C, E, and B. A third memory location stores a dense matrix equal to (ETB+D), where T is an identity matrix and D and T are also portions of the parity check matrix H. First and second parity information is generated in response to receiving information data. Generating the first and second parity information includes accessing the circular content of the portions A, C, E, and B of a parity check matrix H and accessing the circulant column counts of the portions A, C, E, and B.

Efficient LDPC encoder for irregular code

A single instruction is received to read a read address in storage in order to obtain read data and write the read data to a write address in the storage. Error correction decoding is performed in order to obtain user data. Error correction parity information is generated based at least in part on (1) the user data and (2) new metadata associated with the write address, without buffering the user data between the error correction decoding and the generation of the error correction parity information. The user data, the new metadata, and the error correction parity information are stored in the write address in the storage.

Accelerated data copyback

Techniques are described for codeword decoding. In an example, a system computes a checksum for a codeword based on the codeword and a parity check matrix. The system compares the checksum to thresholds. Each threshold is associated with a different decoder from a plurality of decoders available on the system. The system selects a decoder from the plurality of decoders. The decoder is selected based on the comparison of the checksum to the thresholds. The system decodes the codeword by using the selected decoder.

Early selection decoding and automatic tuning

Techniques are described for decoding a message. In one example, the techniques include obtaining a first message comprising a plurality of information bits and a plurality of parity bits, decoding the first message using an iterative decoding algorithm to generate a first bit sequence, generating a miscorrection metric based at least on the first bit sequence and one or more reliability values corresponding to one or more bits in the first message, determining whether a miscorrection happened in the decoder by comparing the miscorrection metric with a first threshold, and upon determining that a miscorrection did not happen, outputting the first bit sequence as a decoded message.

Techniques for low complexity soft decoder for turbo product codes

An apparatus for decoding is disclosed. The apparatus includes a memory and a processor coupled to the memory. The processor is configured to obtain a first codeword comprising one or more information bits and one or more parity bits, obtain a first parameter corresponding to a code rate of the first codeword, and decode the first codeword using a multi-rate decoder to generate a decoded codeword. The multi rate decoder performs a code reconstruction procedure on the first codeword to generate a reconstructed codeword, and decodes the reconstructed codeword. The processor is further configured to output the decoded codeword.

Code reconstruction scheme for multiple code rate TPC decoder

Memory systems may include a memory portion, and a controller suitable for receiving information data, generating first stage data, generating a first portion parity information, generating a second portion parity information based at least in part on the first portion parity information and the first stage data, and outputting the second portion parity information.

Efficient encoder based on modified RU algorithm

Memory systems may include a memory storage, a pre-processing checksum unit suitable for, during a first decoding iteration, receiving hard read data including channel input (Lch) sign values, and computing a checksum of the Lch sign values as a checksum_pre value, and a low-density parity-check (LDPC) decoder including an Lch memory and a checksum update unit, the LDPC decoder suitable for, during the first decoding iteration, storing the Lch sign values in the Lch memory of the LDPC decoder, receiving, with the checksum update unit, the checksum_pre value, and decoding a codeword in at least a second decoding iteration based at least in part on the checksum_pre value computed and received being a parity check on the hard read performed in the first decoding iteration.

VSS LDPC decoder with improved throughput for hard decoding

A first write data and a second write data destined for a first solid state storage channel and a second solid state storage channel, respectively, is received. The first write data is chopped using a chopping factor in order to obtain (1) a first piece of chopped write data destined for the first solid state storage channel and (2) a second piece of chopped write data destined for the first solid state storage channel. The second write data is chopped using the chopping factor in order to obtain (1) a third piece of chopped write data destined for the second solid state storage channel and (2) a fourth piece of chopped write data destined for the second solid state storage channel.

Efficient buffer allocation for NAND write-path system

An apparatus for decoding a TPC codeword is disclosed. The apparatus includes a memory and a processor coupled to the memory. The processor is configured to receive a first set of soft information corresponding to the TPC codeword. The TPC codeword includes at least one codeword corresponding to each of first, second, and third dimensions. The processor is further configured to iteratively perform a first soft decoding procedure on the at least one codeword corresponding to the first dimension to generate a first candidate codeword and upon determining that the first candidate codeword is not a correct codeword, and perform a second decoding procedure on the at least one codeword corresponding to the third dimension to generate a second candidate codeword. The second decoding procedure generates a second set of soft information to be used at a later iteration of the first decoding procedure.

Hybrid soft decoding algorithm for multiple-dimension TPC codes

Memory systems and operating methods thereof comprise a memory storage and an error control coding (ECC) unit. The memory storage stores data which is split into a plurality of data chunks. The error control coding (ECC) unit is suitable for arranging each data chunk into codewords, each data chunk is arranged as part of at least two codewords, and mapping the codewords by reverse indexing the data chunks.

Data mapping scheme for generalized product codes

Techniques are described for optimizing a parity-check matrix for a low density parity check (LDPC) encoder. In an example, a first parity-check matrix is accessed. Based on a set of rules, an independent set of check nodes and variable nodes is determined. The set of rules specifies that a check node associated with the first parity-check matrix belongs to the independent set when the check node is connected to only one variable node from the independent set. The set of rules further specifies that a variable node associated with the first parity-check matrix belongs to the independent set when the variable node is connected to only one check node from the independent set. A size of the independent set is based on the set of rules. A second parity-check matrix is generated by at least applying a permutation to the first parity-check matrix based on the independent set.

Optimization of low density parity-check code encoder based on a search for an independent set of nodes

Growing community of inventors

Fremont, CA, United States of America

Johnson Yen