Sandisk Technologies Inc.

Western Digital Technologies, Inc.

Hua-Ling Cynthia Hsu

YenLung Li

Fanglin Zhang

Min Peng

Huai-Yuan Tseng

Henry Chin

Yu-Chung Lien

Chen Chen

Yingda Dong

Deepanshu Dutta

Jeffrey W Lutze

Daniel Edward Tuers

Changyuan Chen

Siddarth Naga Murty Bassa

Xiang Yang

Abhijeet Manohar

Aaron Lee

Mark Murin

Grishma Shah

Sahil Sharma

A Harihara Sravan

Victor Avila

Masaaki Higashitani

Liang Li

Wei Zhao

Tien-Chien Kuo

Jiacen Guo

Mark Shlick

Tomer Eliash

Jong Hak Yuh

Xuan Tian

Han-Ping Chen

Yen-Lung Li

Erika Penzo

Fanqi Wu

Zhuojie Li

Takayuki Inoue

Jeongduk Sohn

Guanhua Yin

Yanwei He

Kyeongran Yoo

A method of programming a memory device is disclosed herein. The method comprises the steps of: performing a smart verify operation to acquire an initial programming voltage; performing a program operation on a selected wordline starting with the initial programming voltage; performing a bitscan operation of a highest state being verified; and based on a result of the bitscan operation, adjusting the initial programming voltage for programming of subsequent wordlines.

Systems and methods to avoid over programming at infrequent smart verify acquisition for high-performance 3D NAND

Technology for mixed lockout verify. In a first programming phase, prior to a pre-determined data state completing verification, a no-lockout program verify is performed. After the pre-determined data state has completed verification, a lockout program verify is performed. The no-lockout verify may include charging all bit lines associated with the group to a sensing voltage to perform. The lockout verify may include selectively charging to the sensing voltage only bit lines associated with memory cells in the group to be verified. Bit lines associated with memory cells in the group that are not to be verified may be grounded to perform the lockout verify.

Mixed bitline lockout for QLC/TLC die

An apparatus is provided that includes a plurality of memory cells, logic circuits coupled to the memory cells and configured to store 4-bit data in each of the memory cells, and a control circuit coupled to the memory cells and the logic circuits. The control circuit configured to cause the logic circuits to store 3-bit data in each of the memory cells.

Three-bit-per-cell programming using a four-bit-per-cell programming algorithm

A command/address sequence associated with a read/write operation for a memory device that utilizes an existing test data bus in a novel way that obviates the need to utilize an I/O bus for the command/address sequence. As such, the command/address sequence can be performed in parallel with the read/write operations, thereby removing a performance bottleneck that would otherwise be caused by the command and address sequencing. The command/address sequence detects a first enable signal and a data signal on the test data bus and decodes the data signal to obtain at least one of a command latch enable signal and address latch enable signal and at least one of a command code and an address code.

Command and address sequencing in parallel with data operations

For a non-volatile memory that uses hard bit and soft bit data in error correction operations, to reduce the amount of soft bit data that needs to be transferred from a memory to the controller and improve memory system performance, the soft bit data can be compressed before transfer. After the soft bit data is read and stored into the internal data latches associated with the sense amplifiers, it is compressed within these internal data latches. The compressed soft bit data can then be transferred to the transfer data latches of a cache buffer, where the compressed soft bit data can be consolidated and transferred out over an input-output interface. Within the input-output interface, the compressed data can be reshuffled to put into logical user data order if needed.

Use of data latches for plane level compression of soft bit data in non-volatile memories

An apparatus includes a control circuit that is configured to connect to an array of non-volatile memory cells. The control circuit includes a first plurality of data latches configured to connect to non-volatile memory cells of a first plane and a second plurality of data latches configured to connect to non-volatile memory cells of a second plane. The control circuit also includes a shared data transfer data latch configured for transfer of data with the first plurality of data latches and the second plurality of data latches.

Non-volatile memory with shared data transfer latches

For a non-volatile memory that uses hard bit and a soft bit data in error correction operations, architectures are introduced for the compression of the soft bit data to reduce the amount of data transferred over the memory's input-output interface. For a memory device with multiple planes of memory cells, the internal global data bus is segmented and a data compression circuit associated with each segment. This allows soft bit data from a cache buffer of a plane using one segment to transfer data between the cache buffer and the associated compression circuit concurrently with transferring data from a cache buffer of another plane using another segment, either for compression or transfer to the input-output interface.

Architecture and data path options for compression of soft bit data in non-volatile memories

For a non-volatile memory that uses hard bit and a soft bit data in error correction operations, an on-the-fly compression scheme is used for the soft bit data. As soft bit data is transferred to a memory's input-output interface, the soft bit data is compressed prior to transmission to the an ECC engine memory controller, while hard bit data is transferred in un-compressed form.

On-the-fly compression scheme for soft bit data in non-volatile memory

Technology is disclosed for a non-volatile memory system that decouples dataload from program execution. A memory controller transfers data for a program operation and issues a first type of program execution command. When in a coupled mode, the die programs the data in response to the first type of program execution command. When in a decoupled mode, rather than program the data into non-volatile memory cells the die enters a wait state. Optionally, the memory controller can instruct another die to execute a memory operation while the first die is in the wait state. In response to receiving a second type of program execution command from the memory controller when in the wait state, the first die will program the data into non-volatile memory cells. The memory controller may issue the second type of program execution command in response to determining that sufficient power resources (or thermal budget) exist.

Non-volatile storage system with program execution decoupled from dataload

A fast burst program sequence that reduces overall NAND flash programming time is disclosed. The burst program sequence includes maintaining a charge pump in an ON state and not fully discharging the WL/BLs at the conclusion of the programming phase of each program operation. As a result, the fast burst program sequence provides total program time savings over an existing cache program sequence by eliminating the full WL/BL discharge and charge pump reset that conventionally occurs after each program operation, which in turn, allows for the transfer of next page data from the page buffer to the data latches to be hidden within the program time of a prior/current program operation.

Burst programming of a NAND flash cell

On-the-fly multiplexing scheme for compressed soft bit data in non-volatile memories

Use of data latches for compression of soft bit data in non-volatile memories

A non-volatile memory combines a hard bit and a soft bit read into a single, efficient soft sense sequence by using two sense per state level to improve read time efficiency. Rather than a standard hard bit read, where two soft bit reads are performed, offset above and below the hard bit read value, the hard bit read is shifted so that it reliable senses one state but less reliably senses the other state and soft bit data is only determined for the less reliably sensed state. This reduces the amount of soft bit data. The efficient soft sense sequence can be used as a default read mode, providing soft bit information for ECC correction without triggering a read error handling flow. Merging the soft bit and hard bit sense into one sequence can avoid extra overhead for read sequence operations.

Efficient sensing of soft bit data for non-volatile memory

Vertical compression scheme for compressed soft bit data in non-volatile memories with data latch groups

A data storage device including, in one implementation, a NAND memory and a controller. The NAND memory includes a read/write circuit configured to determine and store initial physical column addresses for each plane included in the NAND memory. The controller is configured to send a read-transfer command and a one-byte address to the NAND memory. The read/write circuit is also configured to retrieve a first initial physical column address from the initial physical column addresses stored in the NAND memory after the NAND memory receives the one-byte address from the controller. The first initial physical column address is associated with a die address and a plane address included in the one-byte address. The read/write circuit is further configured to retrieve a first set of data stored at the first initial physical column address. The read/write circuit is also configured to output the first set of data to the controller.

Overhead reduction in data transfer protocol for NAND memory

Growing community of inventors

Fremont, CA, United States of America

Hua-Ling Cynthia Hsu