Samsung Electronics Co., Ltd.

Hyejeong So

Changkyu Seol

Hong Rak Son

Pilsang Yoon

Junjin Kong

Youngdon Choi

Jinsoo Lim

Myoungbo Kwak

Sucheol Lee

Jiyoup Kim

Junghwan Choi

Hongrak Son

Seonghyeog Choi

Donghwan Lee

Hwaseok Oh

Sae-Young Chung

Kwanwoo Noh

Jaehun Jang

Jae Hun Jang

Youngsuk Ra

JongHa Kim

Sungik Choi

Seonghyeong Choi

Lanying Zhao

Encoding and decoding apparatuses and methods for implementing multi-mode coding are provided. The apparatus includes a transmitter and a receiver connected to a data bus. When data bursts are converted by the transmitter into codewords each including a plurality of symbols and/or a codeword received by the receiver is recovered as data bursts, maximum transition avoidance (MTA) codeword mappings in which no maximum transition (MT) event occurs between the plurality of symbols and minimum DC current (MDC) codeword mappings related to minimum power consumption of the plurality of symbols are used.

Encoding and decoding apparatuses and methods for implementing multi-mode coding

Provided is a device and method for encoding and decoding to implement maximum transition avoidance coding with minimum overhead. An exemplary device performs encoding and/or decoding, by using sub-block lookup tables representing correlations between some bit values in a data burst and symbols, a combining lookup table selectively interconnecting the sub-block lookup tables based on remaining bit values of the data burst, and a codeword decoding lookup table designating the sub-block lookup tables corresponding to the symbols of each of received codewords.

Devices and methods for encoding and decoding to implement a maximum transition avoidance coding with minimum overhead

A storage device is provided including a memory controller having a neural processing unit (NPU); a first nonvolatile memory (NVM) connected to the memory controller through a first channel; and a second NVM connected to the memory controller through a second channel. The first NVM stores first weight data for the NPU and the second stores second weight data for the NPU. The memory controller is configured to determine one of the first and second channels that is less frequently accessed upon receiving an inference request from the neural processor, and access a corresponding one of the first weight data and the second weight data using the determined one channel.

Storage device and operating method of storage device

A storage system includes a host device and a storage device. The host device provides first input data for data storage function and second input data for artificial intelligence (AI) function. The storage device stores the first input data from the host device, and performs AI calculation based on the second input data to generate calculation result data. The storage device includes a first processor, a first nonvolatile memory, a second processor and a second nonvolatile memory. The first processor controls an operation of the storage device. The first nonvolatile memory stores the first input data. The second processor performs the AI calculation, and is distinguished from the first processor. The second nonvolatile memory stores weight data associated with the AI calculation, and is distinguished from the first nonvolatile memory.

Storage device with artificial intelligence and storage system including the same

Channel selection information indicate positions of data bits of input data, positions of error correction code (ECC) parity bits for correcting errors in the input data, and positions of state shaping parity bits. The ECC parity bits and the state shaping parity bits are generated to cause a decrease in a quantity of memory cells, of the plurality of memory cells, in which at least one target state among a plurality of states is programmed. An alignment vector is generated based on aligning the data bits of the input data, the ECC parity bits, and the state shaping parity bits, based on the channel selection information. A codeword is generated based on simultaneously performing state shaping and ECC encoding with respect to the alignment vector. Write data are written in the nonvolatile memory device based on the codeword.

Methods of controlling operation of nonvolatile memory devices and data converters for performing the same

A method of decoding may include performing fewer than number of sensing operations of multilevel cells within a nonvolatile memory device, decoding pages corresponding to each of the sensing operations while correcting a channel error using an RIO code, and extracting user data from the decoded pages.

Data coding to reduce read-sensing operations in storage device

A nonvolatile memory device includes a memory cell array including a plurality of memory cells, a row decoder circuit connected to the memory cell array through a plurality of word lines; and a page buffer circuit connected to the memory cell array through bit lines. The row decoder circuit applies read voltages to a selected word line during a read operation. During a read operation performed with respect to each of N logical pages (N being a positive integer) of memory cells connected to the selected word line, the row decoder circuit applies a read voltage from among adjacent N read voltages to the selected word line without applying read voltages other than the adjacent N read voltages to the selected word line. The adjacent N read voltages include a second highest read voltage among the read voltages.

Nonvolatile memory device and operating method of nonvolatile memory device

The operating method of the storage device includes receiving write data to be written at the plurality of memory cells; determining whether the received write data is LSB data to be written at the plurality of memory cells; and encoding the write data according to the determination. The write data is encoded according to the write data when the write data is LSB data to be written at the plurality of memory cells. The write data is encoded according to the write data and encoding data of lower data of the write data to be written at the plurality of memory cells when the write data is not LSB data to be written at the plurality of memory cells.

A memory controller includes a state shaping encoder that receives k-bit write data, selects a logical page with reference to state shape mapping information, and changes data of the logical page to decrease an occurrence probability of a high-order program state among program states used to program the k-bit data in multi-level memory cells.

Memory controller having state shaping engine and method of operating same

An operating method is for a storage device that includes a nonvolatile memory and a memory controller configured to control the nonvolatile memory. The operating method may include the memory controller receiving a read request from an external device, the memory controller adjusting a read scheme according to target data indicated by the read request among data of one page of the nonvolatile memory, and the memory controller reading the target data from the nonvolatile memory according to the adjusted read scheme.

Growing community of inventors

Seoul, South Korea

Hyejeong So