Pre-program pass to reduce system buffer requirements when programming four-level cell (QLC) memory

By performing MLC logic state programming and reading of the first two bits of the four-level unit memory, the problem of large cache demand during QLC memory programming is solved, reducing the bit error rate and cost, and improving the programming reliability.

CN119028405APending Publication Date: 2024-11-26MICRON TECHNOLOGY INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410637904.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2024-04-16
Filing Date
2024-05-22
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The prior art requires a large number of cache buffer resources when programming a four-level cell (QLC) memory, resulting in increased cost and space requirements, and the roughly programmed threshold voltage distribution is difficult to read, resulting in high bit error rates.

Method used

By first roughly programming the threshold voltage distribution of the multilevel unit (MLC) logic state of the first two bits of a specific page of a four-level unit, reading the MLC logic state and determining the QLC logic state from the cache buffer , and then further roughly program the QLC memory unit to reduce cache resource requirements.

Benefits of technology

It effectively reduces the cache requirement during QLC programming, reduces cost and space usage, and reduces the bit error rate after rough programming, and improves programming reliability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119028405A_ABST
    Figure CN119028405A_ABST
Patent Text Reader

Abstract

The invention relates to a pre-program pass to reduce system buffer requirements when programming a four-level cell QLC memory. A memory device includes: a memory array configured as a four-level cell (QLC) memory; and a control logic operably coupled to the memory array. The control logic identifies the first two bits of a particular page of a QLC logic state. The control logic coarsely programs memory cells of the memory array with a threshold voltage profile corresponding to a multi-level cell (MLC) logic state of the first two bits. The control logic reads the MLC logic state from the memory cell and reads latter two bits from a cache buffer to determine the QLC logic state. The control logic causes the memory cells to be further coarse programmed with a QLC threshold voltage profile corresponding to the QLC logic state.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Embodiments of the present disclosure relate generally to memory subsystems, and more specifically, to pre-programming passes to reduce system buffering requirements when programming quad level cell (QLC) memory. Background Art

[0002] The memory subsystem may include one or more memory devices that store data. The memory devices may be, for example, non-volatile memory devices and volatile memory devices. In general, the host system may utilize the memory subsystem to store data at the memory devices and retrieve data from the memory devices. Summary of the invention

[0003] In one aspect, the present application provides a memory device comprising: a memory array configured as a four-level cell (QLC) memory; and control logic operably coupled to the memory array, the control logic being used to perform operations comprising: identifying first two bits of a particular page of a QLC logic state; causing memory cells of the memory array to be coarsely programmed with a threshold voltage distribution of a multi-level cell (MLC) logic state corresponding to the first two bits; reading the MLC logic state from the memory cells and reading second two bits from a cache buffer to determine the QLC logic state; and causing the memory cells to be further coarsely programmed with a QLC threshold voltage distribution corresponding to the QLC logic state.

[0004] In another aspect, the present application provides a method, comprising: identifying, by a memory device, first two bits of a specific page of four-level cell (QLC) logic states; causing memory cells programmed as QLC memory to be coarsely programmed with a threshold voltage distribution of a multi-level cell (MLC) logic state corresponding to the first two bits; reading the MLC logic state from the memory cell and reading the second two bits from a cache buffer to determine the QLC logic state; and causing the memory cell to be further coarsely programmed with a QLC threshold voltage distribution corresponding to the QLC logic state.

[0005] In yet another aspect, the present application provides a computer-readable storage medium storing instructions that, when executed by a processing device of a memory subsystem, cause the processing device to perform operations including: identifying first two bits of a particular page of four-level cell (QLC) logic states; causing memory cells programmed as QLC memory to be coarsely programmed with a threshold voltage distribution of a multi-level cell (MLC) logic state corresponding to the first two bits; reading the MLC logic state from the memory cells and reading last two bits from a cache buffer to determine the QLC logic state; and causing the memory cells to be further coarsely programmed with a QLC threshold voltage distribution corresponding to the QLC logic state. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] The present disclosure will be more fully understood from the detailed description given below and from the accompanying drawings of some embodiments of the present disclosure.

[0007] Figure 1A An example computing system including a memory subsystem in accordance with some embodiments is described.

[0008] Figure 1B is a block diagram of a memory device in communication with a memory subsystem controller of a memory subsystem according to an embodiment.

[0009] Figure 2A to 2B is according to the embodiment as can be used for reference Figure 1B A schematic diagram of a portion of a memory cell array of a memory of the type described.

[0010] Figure 3 is a conceptual depiction of threshold voltage distributions for a plurality of memory cells of a memory array according to an embodiment.

[0011] Figure 4 is a conceptual depiction of threshold voltage distributions of a plurality of memory cells at one stage after programming for use with various embodiments.

[0012] Figure 5A is a graph illustrating an example of a set of threshold voltage distributions that are unreadable after coarse programming in accordance with at least one embodiment.

[0013] Figure 5B is a diagram illustrating the set of threshold voltage distributions ( Figure 5B ) instances.

[0014] Fig. 6A is a diagram illustrating pre-programming passes using multi-level cell (MLC) logic states prior to programming a quad level cell (QLC) memory according to various embodiments.

[0015] Figures 6B to 6E is a table of annotations illustrating different MLC-based encodings that may be converted to QLC-based encodings and thus may be used for pre-programming passes according to various embodiments.

[0016] Figure 7 is a flow chart of a method for performing a pre-programming pass of an MLC logic state before performing coarse programming of a corresponding QLC logic state, according to some embodiments.

[0017] Fig. 8A is a graph illustrating a depiction of threshold voltage distributions for possible QLC logic states after having been pre-programmed with an MLC logic state and then coarsely programmed with a corresponding QLC logic state, according to some embodiments.

[0018] Figure 8B is a note table illustrating the logical bits of a page known to the host system and the logical bits of a page unknown to the host system after having been coarsely programmed to corresponding QLC logical states according to some embodiments.

[0019] Figure 8C is after offsetting the target voltage of the QLC logic state at the QLC logic code transition according to some embodiments. Fig. 8A A chart similar to the one shown in the previous section.

[0020] Fig. 9 is a flow chart of an example method of performing a pre-programming pass of MLC logic states including an optional shifting of target voltage levels of threshold voltage distributions for corresponding QLC logic states in accordance with various embodiments.

[0021] Fig.10 is a block diagram of an example computer system in which embodiments of the present disclosure may operate. DETAILED DESCRIPTION

[0022] Embodiments of the present disclosure relate to pre-programming passes to reduce system buffering requirements when programming quad-level cell (QLC) memory. One or more memory devices may be part of a memory subsystem, which may be a storage device, a memory module, or a hybrid of a memory device and a memory module. Figure 1A Examples of storage devices and memory modules are described. In general, a host system may utilize a memory subsystem that includes one or more components, such as memory devices that store data. The host system may provide data to be stored at the memory subsystem and may request data to be retrieved from the memory subsystem.

[0023] The memory subsystem may include a high-density non-volatile memory device where it is desirable to retain data when no power is supplied to the memory device. An example of a non-volatile memory device is a NAND memory device. Figure 1A to 1B Other examples of nonvolatile memory devices are described. A nonvolatile memory device is a package of one or more dies. Each die may include two or more planes. For some types of nonvolatile memory devices (e.g., NAND devices), each plane includes a set of physical blocks. In some implementations, each block may include multiple sub-blocks. Each plane carries a matrix of memory cells formed on a silicon wafer and connected by conductors called word lines (WL) and bit lines (BL), such that word lines connect multiple memory cells forming rows of the memory cell matrix, and bit lines connect multiple memory cells forming columns of the memory cell matrix.

[0024] Each memory cell can store one or more binary bits of information, depending on the cell type, and have various logic states related to the number of bits stored. The logic states can be represented by binary values ​​(e.g., "0" and "1" or a combination of such values), also referred to herein as logic bit values. Memory cells can be programmed (written) by applying a certain voltage to the memory cells, which causes charge to be stored by the memory cells, thus allowing the voltage distribution generated by the memory cells to be modulated. A group of memory cells, called a memory page, can be programmed together in a single operation (e.g., by selecting consecutive bit lines).

[0025] Precisely controlling the amount of charge stored by a memory cell allows multiple logic levels to be established, thus effectively allowing a single memory cell to store multiple bits of information. A read operation may be performed by comparing a measured threshold voltage (Vt) exhibited by a memory cell to one or more reference voltage levels in order to distinguish between two logic levels of a single level cell (SLC) and multiple logic levels of a multi-level cell. A memory device may include multiple portions, including, for example, one or more portions in which a sub-block is configured as an SLC memory and one or more portions in which a sub-block is configured as a multi-level cell (MLC) memory that can store three bits of information per cell and / or a (three-level cell) TLC memory that can store three bits of information per cell. The voltage levels of the memory cells in the TLC memory form a set of eight programming (or threshold voltage (Vt)) distributions representing eight different combinations of the three bits stored in each memory cell.

[0026] Depending on how the memory cells are configured, each physical memory page in one of the sub-blocks may include multiple page types. For example, a physical memory page formed by SLC memory cells has a single page type called a lower logical page (LP). A multi-level cell (MLC) physical page type may include an LP and an upper logical page (UP) and store two information bits per cell. In addition, a TLC physical page type may include an LP, an UP, and an additional logical page (XP) and store three information bits per cell. In addition, a quad-level (QLC) physical page type may include an LP, an UP, an XP, and a top logical page (TP) and store four information bits per cell. For example, a physical memory page formed by memory cells of a QLC memory type has a total of four logical pages, each of which stores data different from the data stored in other logical pages associated with that physical memory page (referred to herein as a "page"). In addition, a five-level cell (PLC) memory may store five information bits per cell and also include at least LP, UP, and XP.

[0027] In certain memory devices, programming of QLC memory (e.g., memory configured as QLC) is performed in two phases. For example, the two phases may include a coarse phase, in which memory cells are programmed with an initial pass of one or more Vt distributions corresponding to 16 possible QLC logic states. Because the QLC Vt distributions are highly overlapping after coarse programming, these Vt distributions are difficult to read and may result in high bit error rates (BERs) if read from the coarsely programmed Vt distributions. The second phase of programming may be a fine programming operation, in which the QLC Vt distributions are more precisely programmed to a target Vt level associated with each corresponding QLC logic state.

[0028] In these memory devices, since the coarsely programmed Vt distribution will result in a high BER when reading, the memory device in which the QLC Vt distribution is programmed may store the QLC logic state in a cache buffer, such as a static random access memory (SRAM), a tightly coupled memory (TCM), or other type of cache or a combination thereof. Here, a cache buffer may also refer to a non-volatile buffer memory, such as data temporarily stored in SLC or MLC mode, which may eventually be merged into QLC mode in system background operations. In this way, the memory device still knows the QLC logic state data value, which can be used to ensure that fine programming is performed properly. Typical memory devices require a large amount of cache buffer space in order to store the QLC data while performing the above-mentioned two-stage QLC programming, thereby forcing the cost of expensive cache memory that occupies space on a chip with memory configured as QLC. As sub-blocks of memory cells are added to nodes of future memory devices, this demand for caches such as SRAM or TCM may grow exponentially, thereby bringing additional cost and space challenges with the use of QLC memory in the future.

[0029] Aspects of the present disclosure address the above and other deficiencies by performing an initial or pre-programming pass in which MLC logic states are first programmed into memory cells configured as QLC. These MLC logic states may be selected and programmed in a manner that stores specific two of the four bits of the QLC logic state, thereby effectively serving as a cache for half of the QLC data within the NAND memory and correspondingly reducing the need for expensive cache buffer resources. In at least some embodiments, the two bits corresponding to the XP and LP of the QLC logic state are selected as those bits that are programmed into the MLC logic state in this pre-programming pass of the QLC memory.

[0030] In some embodiments, the control logic of the memory device recognizes these two bits (e.g., corresponding to XP and LP) and causes the QLC memory array to be programmed with a threshold voltage (Vt) distribution of MLC logic states, e.g., as a pre-programming pass of the QLC memory array. Because the QLC memory is configured for 16 logic states, the MLC logic states can be located and spaced in a manner that enables the MLC logic states to be reliably read out of the QLC memory array, as will be discussed in greater detail. In this manner, only the other two bits (e.g., TP and UP corresponding to the QLC logic states) are stored in the cache buffer. In these embodiments, the control logic next reads the MLC logic state from the memory array and reads the next two bits (e.g., for TP and UP) from the cache buffer to determine the QLC logic state. In these embodiments, the control logic then causes the memory array to be further coarsely programmed with a QLC threshold voltage distribution corresponding to the QLC logic state.

[0031] In some embodiments, because coarse programming may still produce some BER issues, the coarse programming of some QLC logic states may be adjusted to improve the subsequent reliability of reading out the QLC logic states before fine programming of the QLC logic states. For example, the MLC logic states are no longer stored in the cache buffer and are therefore unknown. Therefore, if no adjustment is made, the transition of the MLC logic states within the QLC logic code is expected to result in a higher BER. Therefore, in some embodiments, the control logic determines that two MLC bits are located at the transition of the MLC logic states within the QLC logic code. In response to that determination, the control logic may shift the target voltage level of the QLC logic state downward by a predetermined voltage (e.g., between 50 and 300 millivolts, depending on the device design) to an updated target voltage level. By performing this shift before coarse programming of the 16 QLC logic states, the risk of reading out the BER of an unknown logic state (involving the MLC coarsely programmed bits) is significantly reduced. Although the risk of the BER of the known two QLC bits (e.g., the TP and UP bits stored in the cache buffer) is increased, these two QLC bits are known and can be read out from the cache before fine programming.

[0032] Thus, advantages of systems and methods implemented in accordance with some embodiments of the present disclosure include, but are not limited to, reducing by 50% the amount of cache (e.g., SRAM / TCM) required to buffer QLC bits while performing QLC coarse and fine programming. This savings in cost and space for the die of a memory device will be exponential as sub-blocks of memory cells are added to memory nodes in future memory device designs. While a small increase in programming time (Tprog) is expected due to the pre-pass programming operation, this small increase in Tprog is outweighed by the cost savings of half (or more) in the cache required to perform QLC programming. Other advantages will be apparent to those skilled in the art of programming memories configured to store multiple bits across different threshold voltage distributions, as will be discussed later.

[0033] Figure 1A An example computing system 100 is illustrated that includes a memory subsystem 110 in accordance with some embodiments of the present disclosure. Memory subsystem 110 may include media such as one or more volatile memory devices (e.g., memory device 140), one or more non-volatile memory devices (e.g., memory device 130), or a combination of such media or memory devices.

[0034] The memory subsystem 110 may be a storage device, a memory module, or a combination of a storage device and a memory module. Examples of storage devices include solid-state drives (SSDs), flash drives, universal serial bus (USB) flash drives, embedded multimedia controller (eMMC) drives, universal flash storage (UFS) drives, secure digital (SD) cards, and hard disk drives (HDDs). Examples of memory modules include dual in-line memory modules (DIMMs), small outline DIMMs (SO-DIMMs), and various types of non-volatile dual in-line memory modules (NVDIMMs).

[0035] The computing system 100 may be a computing device such as a desktop computer, a laptop computer, a network server, a mobile device, a vehicle (e.g., an airplane, drone, train, car, or other transportation vehicle), an Internet of Things (IoT) enabled device, an embedded computer (e.g., a computer included in a vehicle, industrial equipment, or a networked business device), or such a computing device that includes a memory and a processing device.

[0036] The computing system 100 may include a host system 120 coupled to one or more memory subsystems 110. In some embodiments, the host system 120 is coupled to multiple memory subsystems 110 of different types. Figure 1AAn example of a host system 120 coupled to one memory subsystem 110 is illustrated. The host system 120 can provide data to be stored at the memory subsystem 110 and can request data to be retrieved from the memory subsystem 110. As used herein, "coupled to" or "coupled with" generally refers to a connection between components, which can be an indirect communication connection or a direct communication connection (e.g., without intervening components), whether wired or wireless, including connections such as electrical connections, optical connections, magnetic connections, etc.

[0037] The host system 120 may include a processor chipset and a software stack executed by the processor chipset. The processor chipset may include one or more cores, one or more caches, a memory controller (e.g., an NVDIMM controller), and a storage protocol controller (e.g., a PCIe controller, a SATA controller). For example, the host system 120 uses the memory subsystem 110 to write data to the memory subsystem 110 and read data from the memory subsystem 110.

[0038] The host system 120 may be coupled to the memory subsystem 110 via a physical host interface. Examples of the physical host interface include, but are not limited to, a Serial Advanced Technology Attachment (SATA) interface, a Peripheral Component Interconnect Express (PCIe) interface, a Universal Serial Bus (USB) interface, a Fibre Channel, a Serial Attached SCSI (SAS), a Double Data Rate (DDR) memory bus, a Small Computer System Interface (SCSI), a Dual In-line Memory Module (DIMM) interface (e.g., a DIMM slot interface supporting Double Data Rate (DDR)), etc. The physical host interface may be used to transfer data between the host system 120 and the memory subsystem 110. When the memory subsystem 110 is coupled to the host system 120 through a physical host interface (e.g., a PCIe bus), the host system 120 may further utilize an NVM Express (NVMe) interface to access components (e.g., the memory device 130). The physical host interface may provide an interface for passing control, address, data, and other signals between the memory subsystem 110 and the host system 120. Figure 1A Memory subsystem 110 is illustrated. In general, host system 120 can access multiple memory subsystems via the same communication connection, multiple separate communication connections, and / or a combination of communication connections.

[0039] Memory devices 130, 140 may include any combination of different types of non-volatile memory devices and / or volatile memory devices. Volatile memory devices (e.g., memory device 140) may be, but are not limited to, random access memory (RAM), such as dynamic random access memory (DRAM) and synchronous dynamic random access memory (SDRAM).

[0040] Some examples of non-volatile memory devices (e.g., memory device 130) include non-and (NAND) type flash memory and write-in-place memory, such as a three-dimensional cross-point ("3D cross-point") memory device, which is a cross-point array of non-volatile memory cells. The cross-point array of non-volatile memory cells can be combined with a stackable cross-grid data access array to perform bit storage based on changes in body resistance. In addition, compared to many flash-based memories, cross-point non-volatile memory can perform write-in-place operations, where non-volatile memory cells can be programmed without first erasing the non-volatile memory cells. NAND-type flash memory includes, for example, two-dimensional NAND (2D NAND) and three-dimensional NAND (3D NAND).

[0041] Each of the memory devices 130 may include one or more arrays of memory cells. One type of memory cell, such as a single level cell (SLC), may store one bit per cell. Other types of memory cells, such as multi-level cells (MLC), three-level cells (TLC), four-level cells (QLC), and five-level cells (PLC), may store multiple bits per cell. In some embodiments, each of the memory devices 130 may include one or more arrays of memory cells, such as SLC, MLC, TLC, QLC, PLC, or any combination thereof. In some embodiments, a particular memory device may include an SLC portion and an MLC portion, a TLC portion, a QLC portion, or a PLC portion of a memory cell. The memory cells of the memory device 130 may be grouped into pages, which may refer to a logical unit of a memory device used to store data. For some types of memory, such as NAND, pages may be grouped to form blocks.

[0042] Although nonvolatile memory components such as a 3D cross-point array of nonvolatile memory cells and NAND-type flash memory (e.g., 2D NAND, 3D NAND) are described, the memory device 130 may be based on any other type of nonvolatile memory, such as read-only memory (ROM), phase-change memory (PCM), self-select memory, other chalcogenide-based memories, ferroelectric transistor random access memory (FeTRAM), ferroelectric random access memory (FeRAM), magnetic random access memory (MRAM), spin transfer torque (STT)-MRAM, conductive bridging RAM (CBRAM), resistive random access memory (RRAM), oxide-based RRAM (OxRAM), or non-(NOR) flash memory or electrically erasable programmable read-only memory (EEPROM).

[0043] The memory subsystem controller 115 (or simply controller 115) can communicate with the memory device 130 to perform operations such as reading data, writing data, or erasing data and other such operations at the memory device 130. The memory subsystem controller 115 may include hardware, such as one or more integrated circuits and / or discrete components, buffer memory, or a combination thereof. The hardware may include digital circuitry with dedicated (i.e., hard-coded) logic to perform the operations described herein. The memory subsystem controller 115 may be a microcontroller, dedicated logic circuitry (e.g., a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), etc.), or other suitable processor.

[0044] The memory subsystem controller 115 may include a processing device including one or more processors (e.g., processor 117) configured to execute instructions stored in a local memory 119. In the illustrated example, the local memory 119 of the memory subsystem controller 115 includes an embedded memory configured to store instructions for executing various processes, operations, logic flows, and routines that control the operation of the memory subsystem 110, including handling communications between the memory subsystem 110 and the host system 120.

[0045] In some embodiments, local memory 119 may include memory registers that store memory pointers, fetched data, etc. Local memory 119 may also include read-only memory (ROM) for storing microcode. Figure 1A The example memory subsystem 110 in FIG. 1 has been described as including a memory subsystem controller 115, but in another embodiment of the present disclosure, the memory subsystem 110 does not include a memory subsystem controller 115, but may rely on external control (e.g., provided by an external host, or provided by a processor or controller separate from the memory subsystem).

[0046] In general, the memory subsystem controller 115 may receive commands or operations from the host system 120 and may convert the commands or operations into instructions or appropriate commands to achieve the desired access to the memory device 130. The memory subsystem controller 115 may be responsible for other operations associated with the memory device 130, such as wear leveling operations, garbage collection operations, error detection and error correction code (ECC) operations, encryption operations, cache operations, and address translation between logical addresses (e.g., logical block addresses (LBA), namespaces) and physical addresses (e.g., physical block addresses). The memory subsystem controller 115 may further include a host interface circuit system to communicate with the host system 120 via a physical host interface. The host interface circuit system may convert commands received from the host system into command instructions to access the memory device 130, and convert responses associated with the memory device 130 into information for the host system 120.

[0047] The memory subsystem 110 may also include additional circuitry or components not illustrated. In some embodiments, the memory subsystem 110 may include a cache or buffer (e.g., DRAM) and address circuitry (e.g., row decoders and column decoders) that may receive addresses from the memory subsystem controller 115 and decode the addresses to access the memory device 130.

[0048] In some embodiments, the memory device 130 includes a local media controller 135 that operates in conjunction with the memory subsystem controller 115 to perform operations on one or more memory cells of the memory device 130. An external controller (e.g., the memory subsystem controller 115) can manage the memory device 130 externally (e.g., perform media management operations on the memory device 130). In some embodiments, the memory subsystem 110 is a managed memory device, which is a raw memory device 130 with control logic on the die (e.g., the local media controller 135) and a controller for media management (e.g., the memory subsystem controller 115) within the same memory device package. An example of a managed memory device is a managed NAND (MNAND) device.

[0049] In one embodiment, the memory subsystem 110 includes a memory interface component 113. The memory interface component 113 is responsible for handling the interaction of the memory subsystem controller 115 with the memory devices (e.g., memory device 130) of the memory subsystem 110. For example, the memory interface component 113 may send a memory access command (e.g., a program command, a read command, or other command) corresponding to a request received from the host system 120 to the memory device 130. In addition, the memory interface component 113 may receive data from the memory device 130, such as data retrieved in response to a read command or confirmation that a program command was successfully executed. For example, the memory subsystem controller 115 may include a processor 117 (processing device) configured to execute instructions stored in a local memory 119 for performing the operations described herein.

[0050] In at least one embodiment, the memory device 130 includes a QLC program manager 137 configured to perform QLC programming operations, for example, in response to receiving a memory programming command from the memory interface 113. In some embodiments, the local media controller 135 includes at least a portion of the QLC program manager 137 and is configured to perform the functionality described herein. In some embodiments, the QLC program manager 137 is implemented on the memory device 130 using firmware, hardware components, or a combination of the above. In some embodiments, the control logic of the QLC program manager 137 is integrated in whole or in part within the memory subsystem controller 115 and / or the host system 120. In some embodiments, the memory device 130 includes a page buffer 152, which may provide circuitry for programming data to and reading data from memory cells of the memory device 130.

[0051] In various embodiments, memory device 130 includes a cache buffer 154 coupled to local media controller 135 and page buffer 152. In these embodiments, cache buffer 154 includes a cache memory, such as SRAM, TCM, or similar fast access memory. In some embodiments, cache buffer 154 stores QLC data while the QLC data (e.g., QLC logic states) is being programmed to a memory array of memory device 130. By implementing the disclosed techniques and processes, cache buffer 154 can be reduced in half due to the ability to temporarily buffer only half of the QLC data during QLC programming.

[0052] Figure 1B According to an embodiment, a memory subsystem (eg, Figure 1A1 is a simplified block diagram of a first device in the form of a memory device 130 communicating with a second device in the form of a memory subsystem controller 115 of a memory subsystem 110 of an electronic system. Some examples of electronic systems include personal computers, personal digital assistants (PDAs), digital cameras, digital media players, digital recorders, games, appliances, vehicles, wireless devices, mobile phones, and the like. The memory subsystem controller 115 (e.g., a controller external to the memory device 130) may be a memory controller or other external host device.

[0053] Memory device 130 includes a memory cell array 104 that is logically arranged in rows and columns. Memory cells of a logical row are typically connected to the same access line (e.g., word line), while memory cells of a logical column are typically selectively connected to the same data line (e.g., bit line). A single access line may be associated with more than one logical row of memory cells and a single data line may be associated with more than one logical column. Memory cells of at least a portion of memory cell array 104 ( Figure 1B ) can be programmed to one of at least two target data states.

[0054] Row decoding circuitry 108 and column decoding circuitry 111 are provided to decode address signals. Address signals are received and decoded to access memory cell array 104. Memory device 130 also includes input / output (I / O) control circuitry 112 to manage the input of commands, addresses, and data to memory device 130 and the output of data and status information from memory device 130. Address register 114 communicates with I / O control circuitry 112 and row decoding circuitry 108 and column decoding circuitry 111 to latch address signals prior to decoding. Command register 124 communicates with I / O control circuitry 112 and local media controller 135 to latch incoming commands.

[0055] A controller (e.g., a local media controller 135 inside the memory device 130) controls access to the memory cell array 104 in response to a command and generates status information for the external memory subsystem controller 115, i.e., the local media controller 135 is configured to perform an access operation (e.g., a read operation, a program operation, and / or an erase operation) on the memory cell array 104. The local media controller 135 communicates with the row decoding circuitry 108 and the column decoding circuitry 111 to control the row decoding circuitry 108 and the column decoding circuitry 111 in response to an address.

[0056] The local media controller 135 also communicates with the cache registers 118 and the data registers 121. In some embodiments, the cache registers 118 constitute a cache buffer 154 ( Figure 1A) at least a portion of the memory subsystem controller 115. Cache registers 118 latch data (either incoming or outgoing) as directed by local media controller 135 to temporarily store data while memory cell array 104 is busy writing or reading other data, respectively. During a programming operation (e.g., a write operation), data may be transferred from cache registers 118 to data registers 121 for transmission to memory cell array 104; new data from I / O control circuitry 112 may then be latched in cache registers 118. During a read operation, data may be transferred from cache registers 118 to I / O control circuitry 112 for output to memory subsystem controller 115; new data may then be transferred from data registers 121 to cache registers 118. Cache registers 118 and / or data registers 121 may form (e.g., may form at least a portion of) a page buffer 152 of memory device 130. The page buffer 152 may further include a sensing device, such as a sense amplifier, to sense the data state of a memory cell of the memory cell array 104 (e.g., by sensing the state of a data line connected to that memory cell). The state register 122 may communicate with the I / O control circuitry 112 and the local memory controller 135 to latch state information for output to the memory subsystem controller 115.

[0057] The memory device 130 receives control signals from the memory subsystem controller 115 at the local media controller 135 through the control link 132. For example, the control signals may include a chip enable signal CE#, a command latch enable signal CLE, an address latch enable signal ALE, a write enable signal WE#, a read enable signal RE#, and a write protect signal WP#. Depending on the nature of the memory device 130, additional or alternative control signals (not shown) may be further received through the control link 132. In one embodiment, the memory device 130 receives command signals (which represent commands), address signals (which represent addresses), and data signals (which represent data) from the memory subsystem controller 115 through a multiplexed input / output (I / O) bus 134, and outputs the data to the memory subsystem controller 115 through the I / O bus 134.

[0058] For example, a command may be received at I / O control circuitry 112 via input / output (I / O) pins [7:0] of I / O bus 134 and may then be written into command register 124. An address may be received at I / O control circuitry 112 via input / output (I / O) pins [7:0] of I / O bus 134 and may then be written into address register 114. Data may be received at I / O control circuitry 112 via input / output (I / O) pins [7:0] of an 8-bit device or input / output (I / O) pins [15:0] of a 16-bit device and may then be written into cache register 118. The data may then be written into data register 121 for use in programming memory cell array 104.

[0059] In an embodiment, cache register 118 may be omitted and data may be written directly into data register 121. Data may also be output through input / output (I / O) pins [7:0] for an 8-bit device or input / output (I / O) pins [15:0] for a 16-bit device. Although reference may be made to I / O pins, they may include any conductive node that provides an electrical connection to memory device 130 by an external device (e.g., memory subsystem controller 115), such as a commonly used conductive pad or conductive bump.

[0060] Those skilled in the art will appreciate that additional circuitry and signals may be provided and simplified. Figure 1B It should be appreciated that reference Figure 1B The functionality of the various block components described need not necessarily be separated into different components or component portions of an integrated circuit device. For example, a single component or component portion of an integrated circuit device may be adapted to perform Figure 1B Alternatively, one or more components or component parts of an integrated circuit device may be combined to perform Figure 1B Additionally, while specific I / O pins are described according to general conventions for receiving and outputting various signals, it should be noted that other combinations or numbers of I / O pins (or other I / O node structures) may be used in various embodiments.

[0061] Figure 2A to 2B is according to the embodiment as can be used for reference Figure 1B Schematic diagram of a portion of a memory cell array 200A (e.g., a NAND memory array) in a memory of the type described (e.g., as part of memory cell array 104). Memory array 200A includes, for example, word lines 2020 through 202 N The access lines and bit lines 2040 to 204 M The word lines 202 can be connected to the data lines in a many-to-one relationship. Figure 2AFor some embodiments, memory array 200A may be formed on a semiconductor, which may be conductively doped to have a conductivity type such as p-type conductivity, such as to form a p-well, or a conductivity type such as n-type conductivity, such as to form an n-well.

[0062] The memory array 200A may be arranged into rows (each corresponding to a word line 202) and columns (each corresponding to a bit line 204). Each column may include a string of memory cells (eg, nonvolatile memory cells) connected in series, such as NAND strings 2060-206 M Each NAND string 206 can be connected (eg, selectively connected) to a common source (SRC) 216 and can include memory cells 2080-208 N Memory cell 208 may represent a non-volatile memory cell for storing data. The memory cells 208 of each NAND string 206 may be connected in series at a select gate 210 (eg, a field effect transistor) (eg, select gates 2100 to 210 M ) (eg, it may be a source select transistor, commonly referred to as a select gate source) and a select gate 212 (eg, a field effect transistor) (eg, select gates 2120 to 212 M 2100 to 2101) (for example, it can be a drain select transistor, often referred to as a select gate drain). M The select gates 2120 to 2124 may be commonly connected to a select line 214 (eg, a source select line (SGS)), and the select gates 2120 to 2124 may be commonly connected to a select line 214 (eg, a source select line (SGS)). M The select gates 210 and 212 may be commonly connected to a select line 215, such as a drain select line (SGD). Although depicted as conventional field effect transistors, the select gates 210 and 212 may utilize a similar (e.g., identical) structure as the memory cell 208. The select gates 210 and 212 may represent a number of select gates connected in series, where each select gate in the series is configured to receive the same or an independent control signal.

[0063] The source of each select gate 210 can be connected to the common source 216. The drain of each select gate 210 can be connected to the memory cell 2080 of the corresponding NAND string 206. For example, the drain of the select gate 2100 can be connected to the memory cell 2080 of the corresponding NAND string 2060. Thus, each select gate 210 can be configured to selectively connect the corresponding NAND string 206 to the common source 216. The control gate of each select gate 210 can be connected to the select line 214.

[0064] The drain of each select gate 212 can be connected to the bit line 204 of the corresponding NAND string 206. For example, the drain of select gate 2120 can be connected to the bit line 2040 of the corresponding NAND string 2060. The source of each select gate 212 can be connected to the memory cell 208 of the corresponding NAND string 206. N For example, the source of the select gate 2120 may be connected to the memory cell 208 of the corresponding NAND string 2060. N Thus, each select gate 212 can be configured to selectively connect a corresponding NAND string 206 to a corresponding bit line 204. The control gate of each select gate 212 can be connected to a select line 215.

[0065] Figure 2A The memory array 200A in can be a quasi-two-dimensional memory array and can have a substantially planar structure, such as where the common source 216, NAND strings 206, and bit lines 204 extend in substantially parallel planes. Alternatively, Figure 2A The memory array 200A in can be a three-dimensional memory array, for example, where the NAND strings 206 can extend substantially perpendicular to a plane containing the common source 216 and a plane containing the bit lines 204 (which can be substantially parallel to the plane containing the common source 216).

[0066] The typical construction of memory cell 208 includes a data storage structure 234 (e.g., a floating gate, a charge trap, and the like) that can determine the data state of the memory cell (e.g., by a change in threshold voltage) and a control gate 236, such as Figure 2A . The data storage structure 234 may include both conductive and dielectric structures, while the control gate 236 is typically formed of one or more conductive materials. In some cases, the memory cell 208 may further have a defined source / drain (e.g., source) 230 and a defined source / drain (e.g., drain) 232. The memory cell 208 has a control gate 236 connected to (and in some cases forming) the word line 202.

[0067] A column of memory cells 208 may be a NAND string 206 or a number of NAND strings 206 that are selectively connected to a given bit line 204. A row of memory cells 208 may be memory cells 208 that are commonly connected to a given word line 202. A row of memory cells 208 may (but need not) include all of the memory cells 208 that are commonly connected to a given word line 202. A row of memory cells 208 may generally be divided into one or more groups of physical pages of memory cells 208, and a physical page of memory cells 208 generally includes every other memory cell 208 that is commonly connected to a given word line 202. For example, a row of memory cells 208 that is commonly connected to a word line 202 may be divided into one or more groups of physical pages of memory cells 208, and a physical page of memory cells 208 generally includes every other memory cell 208 that is commonly connected to a given word line 202. NThe memory cells 208 selectively connected to the even bit lines 204 (eg, bit lines 2040, 2042, 2044, etc.) may be one physical page of memory cells 208 (eg, even memory cells), while the memory cells 208 commonly connected to the word line 202 may be one physical page of memory cells 208 (eg, even memory cells). N And the memory cells 208 selectively connected to the odd bit lines 204 (eg, bit lines 2041 , 2043 , 2045 , etc.) may be another physical page of the memory cells 208 (eg, odd memory cells).

[0068] although Figure 2A 2043 to 2045 are not explicitly depicted in the figure, but it can be understood from the figure that the bit lines 204 of the memory cell array 200A can be numbered consecutively from bit line 2040 to bit line 204. M . Other groupings of memory cells 208 commonly connected to a given word line 202 may also define a physical page of memory cells 208. For some memory devices, all memory cells commonly connected to a given word line may be considered a physical page of memory cells. The portion of a physical page of memory cells (which may still be an entire row in some embodiments) that is read during a single read operation or programmed during a single program operation (e.g., an upper or lower page of memory cells) may be considered a logical page of memory cells. A block of memory cells may include those memory cells that are configured to be erased together, such as those connected to word lines 2020 through 2021. N All memory cells of a common word line 202 (e.g., all NAND strings 206 that share a common word line 202). Unless explicitly distinguished, references herein to a page of memory cells refer to memory cells of a logical page of memory cells. Although discussed in conjunction with NAND flash memory Figure 2A Examples of, but the embodiments and concepts described herein are not limited to a particular array architecture or structure, and may include other structures (e.g., SONOS, phase change, ferroelectric, etc.) and other architectures (e.g., AND arrays, NOR arrays, etc.).

[0069] Figure 2B Is it possible to use it as a reference Figure 1B Another schematic diagram of a portion of a memory cell array 200B in a memory of the type described (eg, as part of memory cell array 104). Figure 2B The same numbered elements in correspond to those in Figure 2A Description provided. Figure 2BAdditional details of one example of a three-dimensional NAND memory array structure are provided. The three-dimensional NAND memory array 200B can incorporate a vertical structure that can include semiconductor pillars, where a portion of the pillars can serve as a channel region for the memory cells of the NAND string 206. The NAND string 206 can each be selectively connected to the bit lines 2040 to 2044 through a select transistor 212 (e.g., which can be a drain select transistor, commonly referred to as a select gate drain). M , and connected to a common source 216 through a select transistor 210 (e.g., which may be a source select transistor, often referred to as a select gate source). Multiple NAND strings 206 may be selectively connected to the same bit line 204. Subsets of NAND strings 206 may be selectively connected to the same bit line 204 by biasing select lines 2150 to 215 K The word lines 202 are connected to their respective bit lines 204 to selectively activate a particular select transistor 212 between each NAND string 206 and the bit line 204. The select transistors 210 can be activated by biasing the select line 214. In some embodiments, each sub-block or string of memory cells has a select line 214 separate from other sub-blocks or strings. In some embodiments, a pair of sub-blocks share a select line 214. Each word line 202 can be connected to multiple rows of memory cells of the memory array 200B. Rows of memory cells that are generally connected to each other by a particular word line 202 can be collectively referred to as a level.

[0070] Figure 3 is a conceptual depiction of the threshold voltage ranges for a number of memory cells. Figure 3 An example of threshold voltage ranges and their distribution for a group of sixteen-level memory cells (e.g., QLC memory cells) is illustrated. For example, such memory cells may be programmed to fall within sixteen ("16") different threshold voltage ranges 3300 to 330 15 Each threshold voltage range is used to represent a data state corresponding to a bit pattern of four bits. Threshold voltage range 3300 generally has a higher threshold voltage (Vt) than the remaining threshold voltage ranges 3301 to 330 15 The greater width is because typically all of the memory cells are placed into data states corresponding to the threshold voltage range 3300, and then a subset of those memory cells are subsequently programmed to have a threshold voltage range 3301 to 3300. 15 Since programming operations are generally more gradually controlled than erase operations, these threshold voltage ranges 3301 to 330 15 may tend to have a tighter distribution.

[0071] Data Status Logical data value Data Status Logical data value L0 1111 L8 0110 L1 1110 L9 0100 L2 1010 L10 1100 L3 1000 L11 1101 L4 1001 L12 0101 L5 0001 L13 0111 L6 0000 L14 0011 L7 0010 L15 1011

[0072] Table 1

[0073] Threshold voltage range 3300, 3301, 3302, 3303, 3304, 3305, 3306, 3307, 3308, 3309, 330 10 ,330 11 ,330 12 ,330 13 ,330 14 and 330 15 Each may represent a corresponding data state (e.g., Vt level), such as L0, L1, L2, L3, L4, L5, L6, L7, L8, L9, L10, L11, L12, L13, L14, and L15. As an example, if the threshold voltage of the memory cell is within the first of the sixteen threshold voltage ranges 3300, then in this case the memory cell may store a data state L0 having a logic data value of '1111' and is generally referred to as an erased state of the memory cell. If the threshold voltage is within the second of the sixteen threshold voltage ranges 3301, then in this case the memory cell may store a data state L1 having a logic data value of '1110'. If the threshold voltage is within the third of the sixteen threshold voltage ranges 3302, then in this case the memory cell may store a data state L2 having a logic data value of '1010', and so on. Table 1 provides one possible correspondence (e.g., encoding) between data states and their corresponding logic data values ​​(or logic states). Other assignments of data states (e.g., Vt levels) to logical data values ​​(e.g., logical bit patterns) are known or contemplated. As used herein, a memory cell remaining in a lowest data state (e.g., an erased state or L0 data state) will be considered to be programmed to the lowest data state.

[0074] Figure 4 is a conceptual depiction of the threshold voltage distribution of a plurality of memory cells after a programming operation. Figure 4 The threshold voltage distribution 430 d to 430 d+1 Can indicate when the programming operation for a memory cell is completed Figure 3 The threshold voltage range is 3300 to 330 15 A certain part of the distribution of . Figure 4 , when programming is complete, adjacent threshold voltage distributions 430 are typically separated by a certain read window margin 432 (e.g., dead zone). Applying a sensing voltage (e.g., a read level voltage) within the read window margin 432 to the control gates of multiple memory cells can be used to distinguish the threshold voltage distributions 430. d (and any lower threshold voltage distributions) and threshold voltage distributions 430 d+1 (and any higher threshold voltage distributions) of memory cells.

[0075] Due to a phenomenon called slow charge loss (SCL), the threshold voltage of a memory cell changes over time as the charge of the cell degrades, which is referred to as a "temporary voltage shift" (because the degraded charge shifts the voltage distribution along the voltage axis toward a lower voltage level). The threshold voltage changes rapidly at first (immediately after the memory cell is programmed, referred to as quick charge loss (QLC)), and then slows down in an approximately log-linear manner with respect to the time that has passed since the cell programming event. This temporary voltage shift reduces the threshold voltage distribution 430 over time. d to 430 d+1 The read window margin 432 between the two threshold voltage distributions may be increased, and these threshold voltage distributions may be caused to overlap, thereby making it more difficult to distinguish between adjacent threshold voltage distributions.

[0076] Figure 5A is a graph illustrating an example of a set of threshold voltage distributions that are unreadable after coarse programming according to at least one embodiment. Coarse programming can be compared to an initial pass programming where the Vt distributions are highly overlapped when many Vt distributions are coarsely programmed (e.g., in the case of programming a QLC or PLC memory). Due to this overlap of Vt distributions, several sets of coarsely programmed threshold Vt distributions may also be referred to herein as intermediate Vt distributions. This overlap occurs due to less precise programming, where each Vt distribution broadly covers a threshold voltage range that roughly approximates a more accurate (finer) threshold voltage range intended for each respective Vt distribution.

[0077] Figure 5B is a diagram illustrating the set of threshold voltage distributions ( Figure 5B ). When fine programming is completed (e.g., to the last set of Vt distributions), each Vt distribution is more finely defined within the focused threshold voltage range for each respective logic state. When this happens, the read window margin between the respective Vt distributions widens, so that the individual logic states of different memory cells across a group of memory cells can be distinguished when reading. Figure 5A A higher BER may occur when reading the logic state from a coarsely programmed Vt distribution, but Figure 5B A lower BER would be expected when reading out the logic state of the finely programmed logic state.

[0078] Fig. 6A is a diagram illustrating a pre-programming pass using multi-level cell (MLC) logic states prior to programming to quad level cell (QLC) memory according to various embodiments. Figures 6B to 6Eis a note table illustrating different MLC-based encodings that may be converted to QLC-based encodings and thus may be used for pre-programming passes according to various embodiments. As illustrated, in some embodiments, due to the potential grouping of XP / LP bits, the MLC logic states for the pre-programming pass are typically derived from the Extra Page (XP) and Lower Page (LP) bits in order, as will be referred to in Figures 6B to 6E With different QLC logic encodings, different page bits may be selected for grouping, such as TP / XP, XP / UP, TP / LP, UP / LP, etc. Therefore, the present disclosure is not limited to using only the XP / LP bits of the QLC encoding for MLC logic state encoding.

[0079]

[0080] Table 2

[0081] However, as an exemplary embodiment, the XP / LP based MLC bits may be variably used as the initial QLC encoding according to Table 2. As can be observed, the MLC logic state adapts starting from the lower corresponding QLC logic state, as follows. Regarding MLC logic state "11", Fig. 6A The erased data state (L0) illustrated at the top of FIG. 1 is the only lower QLC logic state that contains the "11" encoding and is therefore used for the first MLC logic state. Figure 6B , the XP / LP bits of QLC data states L11, L12, and L13 also have an encoding of "11." Thus, as illustrated in Table 2, the QLC erase state (L0) may initially represent all four of these QLC data states with their corresponding QLC logical states.

[0082] With respect to the MLC logic state "01", the XP / LP bits of the QLC data state L4 are the lowest QLC logic states with a "01" encoding (see Fig. 6A ). Figure 6C As illustrated by the dashed line 630 in FIG. 1 , the XP / LP bits of the QLC data state L5 also have a "01" encoding. Figure 6C , the XP / LP bits of QLC data states L14 and L15 also have a "01" encoding. Thus, as illustrated in Table 2, QLC data state L4 may initially represent all four of these QLC data states with their corresponding QLC logic states.

[0083] With respect to MLC logic state "10", the XP / LP bit of QLC data state L1 is the lowest QLC logic state with a "10" encoding (see Fig. 6A ). Fig.6D, the XP / LP bits of QLC data states L8, L9, and L10 also have a "10" encoding, as illustrated by dashed line 640 in TABLE 2. Thus, as illustrated in TABLE 2, QLC data state L1 may initially represent all four of these QLC data states with their corresponding QLC logic states.

[0084] With respect to the MLC logic state "00", the XP / LP bits of the QLC data state L2 are the lowest QLC logic states with a "00" encoding (see Fig. 6A ). Although data state L3 may also be used and is lower than data state L4, if the result of the QLC logic state to be programmed is L2, charge is generally not removed to fully program the Vt distribution. Fig. 6E As shown by the dashed line 650, the XP / LP bits of QLC data state L3 also have "00" encoding. Fig. 6E , the XP / LP bits of QLC data states L6 and L7 also have "00" encodings, as illustrated by dashed line 652 in TABLE 2. Thus, as illustrated in TABLE 2, QLC data state L2 may initially represent all four of these QLC data states with their corresponding QLC logic states.

[0085] like Fig. 6A , the MLC encoding generally corresponds to the L0, L4, L1, and L2 data states, but can be programmed to be wider, such as each MLC distribution covering the threshold voltage range of approximately two QLC Vt distributions. By allowing wider distributions, the pre-programmed MLC operation can be completed with fewer programming pulses. For example, the XP / LP bits of the MLC encoding "10" correspond to the QLC data state L1, extending down to voltage level R1, which is illustrated by dashed line 601. Similarly, the XP / LP bits of the MLC encoding "00" correspond to the QLC data state L2, extending down to voltage level R2, which is illustrated by dashed line 602. Finally, the XP / LP bits of the MLC encoding "01" correspond to the QLC data state L4, extending down to voltage level R3, which is illustrated by dashed line 603.

[0086] Therefore, in this example embodiment and with continued reference to Fig. 6A, some constraints may be placed on the initial programming manner of the MLC logic state (e.g., the disclosed pre-programming pass) to ensure that the MLC logic state can both be reliably read back from the memory cell and programmed to a voltage level that is not too high for any given target QLC threshold voltage (Vt) distribution. In these embodiments, the control logic (e.g., QLC programming manager 137) ensures that the threshold voltage distribution is programmed to be no higher than the fifth threshold voltage distribution of possible QLC logic states (e.g., corresponding to data state L4). This ensure may include, for example, forcing the upper tail of the highest of the possible MLC threshold voltage distributions to be programmed to be no higher than the upper tail of the fifth threshold voltage distribution of possible QLC logic states. As previously discussed, such constraints ensure that the MLC pre-pass Vt level is no higher than the corresponding Vt target voltage for the corresponding QLC logic state.

[0087] Furthermore, in some embodiments, the control logic causes the read voltage levels for each of the top three possible threshold voltage distributions for the MLC logic state(s) (e.g., corresponding to the L4, L1, and L2 QLC data states) to be evenly spaced within a threshold percentage. For example, with a wider Vt distribution for an MLC pre-programming pass, while the MLC logic state "01" (dashed line 603) may remain approximately in the same position, the "10" and "00" logic states (dashed lines 601 and 602) may shift to a lower voltage. Furthermore, the first width between each of the read voltage levels for the top three possible threshold voltage distributions may be permitted to be at least twice as wide as the second width between each of the read voltage levels for the corresponding QLC logic state. Fig. 6A As illustrated in , the spacing between the R1 and R2 voltage levels and between the R2 and R3 voltage levels can be 2.5 times wider than a typical QLC Vt distribution.

[0088] Figure 7 7 is a flow chart of a method 700 for performing a pre-programming pass of an MLC logic state before performing a coarse programming of a corresponding QLC logic state, according to some embodiments. The method 700 may be performed by processing logic, which may include hardware (e.g., a processing device, circuitry, dedicated logic, programmable logic, microcode, hardware of a device, an integrated circuit, etc.), software (e.g., instructions run or executed on a processing device), or a combination thereof. In some embodiments, the method 700 is performed by Figure 1A to 1BThe local media controller 135 (e.g., control logic) (e.g., QLC program manager 137) of the embodiment is executed on a memory array including a plurality of memory cells electrically coupled to a plurality of word lines and a plurality of bit lines. Although shown in a particular sequence or order, the order of the processes may be modified unless otherwise specified. Therefore, the illustrated embodiments should be understood to be merely examples, and the illustrated processes may be performed in a different order, and some processes may be performed in parallel. In addition, one or more processes may be omitted in various embodiments. Therefore, not all processes are required in every embodiment. Other flows are possible.

[0089] At operation 710, two QLC bits are identified. More specifically, processing logic identifies the first two bits of a particular page of four-level cell (QLC) logic states. Although the examples herein illustrate the use of QLC-encoded extra page (XP) and lower page (LP) bits, other combinations of two QLC bits may be considered, as previously discussed.

[0090] At operation 720, the memory cells are programmed with the MLC logic states. More specifically, the processing logic causes the memory cells programmed as QLC memory to be coarsely programmed with a threshold voltage distribution corresponding to the MLC logic states of the first two bits.

[0091] At operation 730, the QLC logic state is determined. More specifically, processing logic reads the MLC logic state from the memory cell (which is the first two bits) and reads the second two bits from the cache buffer to determine the QLC logic state. In some embodiments, the cache buffer is cache buffer 154 ( Figure 1A ) or cache register 118 ( Figure 1B ). Therefore, in these embodiments, the processing logic also initially stores only the last two of the four bits of the QLC logic state in the cache buffer. In this way, the processing logic accesses all four bits of the QLC logic state to then be able to determine the corresponding QLC threshold voltage distribution to be coarsely programmed.

[0092] At operation 740, the memory cell is further coarsely programmed. More specifically, processing logic causes the memory cell to be further coarsely programmed with a QLC threshold voltage distribution corresponding to a QLC logic state.

[0093] Fig. 8A is a graph illustrating a depiction of threshold voltage distributions for possible QLC logic states after having been pre-programmed with an MLC logic state and then coarsely programmed with a corresponding QLC logic state, according to some embodiments. Figure 8Bis a note table illustrating the logical bits of a page known to the host system 120 (e.g., TP / UP) and the logical bits of a page unknown to the host system 120 (e.g., XP / LP) after having been coarsely programmed to corresponding QLC logical states according to some embodiments. Because the XP / LP bits are unknown, transitions of MLC logical states within the QLC logical encoding will result in high bit error rates (BERs) without the ability to correct erroneously read logical states. For example, there will be a higher BER at the transition data states of L1, L3, L5, L7, L10, L13, for example because the upper tail of these data states will transition to the new MLC logical state of the XP / LP bits.

[0094] Figure 8C is the target voltage offset of the QLC logic state at the QLC logic code transition according to some embodiments. Fig. 8A . In these embodiments, to address the high BER suffered when attempting to read a coarsely programmed state after pre-programming the 16 QLC logic states and then coarse programming, memory device 130 may first determine whether the MLC logic state (e.g., the XP / LP bit programmed in the pre-programming pass) is in one of these transition data states in the QLC encoding, such as L1, L3, L5, L7, L10, or L13. In some embodiments, if the MLC logic state matches one of these transition data states, memory device 130 shifts the target voltage level of the QLC logic state to be programmed downward, such as by a predetermined voltage (e.g., somewhere between 50 and 200 mV) to an updated target voltage level, depending on the memory device design and the read window budget between these logic states that may be required.

[0095] Figure 8C 15. The top 15 threshold voltage distributions of the QLC data states L1 to L15 are illustrated. The high BER states L1, L3, L5, L7, L10, and L13 have been shifted to the left by about the same predetermined voltage. Because these high BER states are now well spaced from each other, the risk of high BER is reduced to a level comparable to the threshold distributions after the fine programming phase, which can be corrected by error code correction (ECC). It may be noted that some of the normal BER states (e.g., L2, L4, L6, L9, L12) overlap heavily with one of the shifted high BER states. An error in reading one of the normal BER states is forgivable because the memory device 130 can access the TP / UP bits in the cache buffer 154 and combine them with the MLC coding read out of the memory cell after the pre-programming pass. In this way, the memory device 130 can determine what the QLC logic state should be before performing fine programming of the QLC logic state after coarse programming.

[0096] Fig. 9 900 is a flow chart of an example method 900 of performing a pre-programming pass of an MLC logic state, the method including an optional offset of a target voltage level of a threshold voltage distribution of a corresponding QLC logic state, according to various embodiments. The method 900 may be performed by processing logic, which may include hardware (e.g., a processing device, a circuit system, a dedicated logic, a programmable logic, a microcode, hardware of a device, an integrated circuit, etc.), software (e.g., instructions run or executed on a processing device), or a combination thereof. In some embodiments, the method 900 is performed by Figure 1A to 1B The local media controller 135 (e.g., control logic) (e.g., QLC program manager 137) of the embodiment is executed on a memory array including a plurality of memory cells electrically coupled to a plurality of word lines and a plurality of bit lines. Although shown in a particular sequence or order, the order of the processes may be modified unless otherwise specified. Therefore, the illustrated embodiments should be understood to be merely examples, and the illustrated processes may be performed in a different order, and some processes may be performed in parallel. In addition, one or more processes may be omitted in various embodiments. Therefore, not all processes are required in every embodiment. Other flows are possible.

[0097] At operation 910, two QLC bits are identified. More specifically, processing logic identifies the first two bits of a particular page of four-level cell (QLC) logic states. Although the examples herein illustrate the use of QLC-encoded extra page (XP) and lower page (LP) bits, other combinations of two QLC bits may be considered, as previously discussed.

[0098] At operation 920, the memory cells are programmed with the MLC logic state. More specifically, processing logic causes memory cells of the memory array to be coarsely programmed with a threshold voltage distribution corresponding to the multi-level cell (MLC) logic state of the first two bits.

[0099] At operation 930, the QLC logic state is determined. More specifically, processing logic reads the MLC logic state (first two bits) from the memory cell and reads the second two bits from the cache buffer to determine the QLC logic state. In some embodiments, the cache buffer is cache buffer 154 ( Figure 1A ) or cache register 118 ( Figure 1B ). Therefore, in these embodiments, the processing logic also initially stores only the last two of the four bits of the QLC logic state in the cache buffer. In this way, the processing logic accesses all four bits of the QLC logic state to then be able to determine the corresponding QLC threshold voltage distribution to be coarsely programmed.

[0100] In some embodiments of method 900, processing logic also determines that the last two bits read from the cache buffer are incorrect. Processing logic can then update the QLC threshold voltage distribution for the QLC logic state based on the correct values ​​of the last two bits, which produces an updated QLC threshold voltage distribution that can be used at operation 990 to perform fine programming of the memory cell to the updated QLC threshold voltage distribution.

[0101] At operation 940, the first two bits are checked for transitions. More specifically, processing logic determines whether the first two bits are located at a transition of an MLC logic state within a QLC logic encoding (eg, a Gray encoding of QLC data states).

[0102] At operation 950, the QLC target voltage is shifted. More specifically, in response to determining at operation 940 that the first two bits are at a transition of an MLC logic state within the QLC logic code, processing logic shifts the target voltage level of the QLC logic state downward by a predetermined voltage to an updated target voltage level.

[0103] At operation 960, the memory cells are coarsely programmed. More specifically, processing logic causes the memory cells to be further coarsely programmed with a QLC threshold voltage distribution corresponding to the updated target voltage level.

[0104] At operation 970, the memory cell is coarsely programmed without a previous Vt shift. More specifically, in response to determining at operation 940 that the first two bits are not at a transition of an MLC logic state within the QLC logic code, processing logic causes the memory cell to be further coarsely programmed with a QLC threshold voltage distribution corresponding to the QLC logic state.

[0105] At operation 980, the coarse programmed state is optionally read. More specifically, the processing logic reads the QLC threshold voltage distribution that has been coarsely programmed to the memory cells at the updated target voltage level (if the method 900 passed through operation 950) or the default Vt level corresponding to the QLC logic state (if the method 900 passed through operation 970).

[0106] At operation 990, the memory cells are fine programmed. More specifically, the processing logic causes the memory cells to be fine programmed with a QLC threshold voltage distribution.

[0107] Fig.10 An example machine illustrating a computer system 1000 in which a set of instructions for causing the machine to perform any one or more of the methodologies discussed herein may be executed. In some embodiments, the computer system 1000 may correspond to a host system (e.g., Figure 1A1) a host system 120 that includes, is coupled to, or utilizes a memory subsystem (e.g., Figure 1A The memory subsystem 110 of the controller may be used to execute the operation of the controller (for example, execute the operating system to execute the corresponding Figure 1A In some embodiments, the machine may be connected (e.g., using a network) to other machines in a LAN, an intranet, an extranet, and / or the Internet. The machine may operate in the capacity of a server or a client machine in a client-server network environment, as a peer machine in a peer-to-peer (or distributed) network environment, or as a server or a client machine in a cloud computing infrastructure or environment.

[0108] The machine may be a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), a cellular phone, a network appliance, a server, a network router, a switch or a bridge, or any machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine. Furthermore, while a single machine is described, the term "machine" shall also be taken to include any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein.

[0109] The example computer system 1000 includes a processing device 1002, a main memory 1004 (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM) (e.g., synchronous DRAM (SDRAM) or Rambus DRAM (RDRAM)), etc.), a static memory 1010 (e.g., flash memory, static random access memory (SRAM), etc.), and a data storage system 1018, which communicate with each other via a bus 1030.

[0110] The processing device 1002 represents one or more general-purpose processing devices, such as a microprocessor, a central processing unit, or the like. More specifically, the processing device may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, or a processor that implements other instruction sets or a processor that implements a combination of instruction sets. The processing device 1002 may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP), a network processor, or the like. The processing device 1002 is configured to execute instructions 1028 for performing the operations and steps discussed herein. The computer system 1000 may further include a network interface device 1008 for communicating over a network 1020.

[0111] The data storage system 1018 may include a machine-readable storage medium 1024 (also referred to as a non-transitory computer-readable storage medium) having stored thereon one or more sets of instructions 1026 or software embodying any one or more of the methodologies or functions described herein, including those associated with the QLC program manager 137. The data storage system 1018 may further include the local media controller 135 and page buffer 152 discussed previously. The instructions 1028 may also reside, completely or at least partially, within the main memory 1004 and / or within the processing device 1002 during execution by the computer system 1000, the main memory 1004 and the processing device 1002 also constituting machine-readable storage media. The machine-readable storage medium 1024, the data storage system 1018, and / or the main memory 1004 may correspond to Figure 1A Memory subsystem 110.

[0112] In one embodiment, the instructions 1026 include instructions for implementing a command corresponding to a controller (e.g., Figure 1A The machine-readable storage medium 1024 is shown as a single medium in the example embodiment, but the term "machine-readable storage medium" should be considered to include a single medium or multiple media storing one or more sets of instructions. The term "machine-readable storage medium" should also be considered to include any medium capable of storing or encoding a set of instructions for machine execution and causing the machine to perform any one or more methodologies of the present disclosure. Therefore, the term "machine-readable storage medium" should be considered to include, but not limited to, solid-state memory, optical media, and magnetic media.

[0113] Some portions of the foregoing detailed description have been presented in terms of algorithms and symbolic representations of operations on data bits within a computer memory. These algorithmic descriptions and representations are the means used by those skilled in the art of data processing to most effectively convey the substance of their work to others skilled in the art. An algorithm is generally considered herein to be a self-consistent sequence of operations leading to a desired result. The operations are those requiring physical manipulation of physical quantities. Typically, although not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, combined, compared, and otherwise manipulated. Mainly for common purposes, it sometimes proves convenient to refer to these signals as bits, values, elements, symbols, characters, items, numbers, or the like.

[0114] It should be remembered, however, that all of these and similar terms are associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. The present disclosure may be directed to the actions and processes of a computer system or similar electronic computing device that manipulates and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer system's memories or registers or other such information storage systems.

[0115] The present disclosure also relates to an apparatus for performing the operations described herein. This apparatus may be specially constructed for the intended purpose, or it may comprise a general purpose computer selectively activated or reconfigured by a computer program stored in the computer. This computer program may be stored in a computer-readable storage medium, such as, but not limited to, any type of disk, including floppy disks, optical disks, CD-ROMs and magneto-optical disks, read-only memories (ROMs), random access memories (RAMs), EPROMs, EEPROMs, magnetic or optical cards, or any type of medium suitable for storing electronic instructions, each coupled to a computer system bus.

[0116] The algorithms and displays presented herein are not inherently related to any particular computer or other device. Various general purpose systems may be used with programs according to the teachings herein, or it may prove convenient to build more specialized equipment to perform the methods. The structures of a variety of these systems will appear as described in the following description. In addition, the present disclosure is not described with reference to any particular programming language. It will be appreciated that a variety of programming languages ​​may be used to implement the teachings of the present disclosure as described herein.

[0117] The present disclosure may be provided as a computer program product or software that may include a machine-readable medium having instructions stored thereon, which instructions may be used to program a computer system (or other electronic device) to perform a process according to the present disclosure. A machine-readable medium includes any mechanism for storing information in a form readable by a machine (e.g., a computer). In some embodiments, a machine-readable (e.g., computer-readable) medium includes a machine (e.g., computer) readable storage medium, such as a read-only memory ("ROM"), a random access memory ("RAM"), a magnetic disk storage medium, an optical storage medium, a flash memory device, etc.

[0118] In the foregoing description, embodiments of the present disclosure have been described with reference to specific example embodiments thereof. It will be apparent that various modifications may be made to the present disclosure without departing from the broader spirit and scope of the embodiments of the present disclosure as set forth in the appended claims. Accordingly, the description and drawings should be regarded in an illustrative rather than a restrictive sense.

Claims

1. A memory device, comprising: a memory array configured as a quad-level cell (QLC) memory; and Control logic operably coupled to the memory array, the control logic to perform operations including: The first two bits identify a specific page of QLC logical state; causing memory cells of the memory array to be coarsely programmed with a threshold voltage distribution corresponding to a multi-level cell (MLC) logic state of the first two bits; reading the MLC logic state from the memory cell and reading the next two bits from a cache buffer to determine the QLC logic state; and The memory cell is further coarsely programmed with a QLC threshold voltage distribution corresponding to the QLC logic state.

2. The memory device of claim 1, wherein the operations further comprise storing only the last two bits of four bits of the QLC logic state in the cache buffer.

3. The memory device of claim 1, wherein the operations further comprise ensuring that the threshold voltage distribution is programmed to a fifth threshold voltage distribution no higher than a possible QLC logic state.

4. The memory device of claim 3, wherein the ensuring comprises forcing an upper tail of a highest of possible MLC threshold voltage distributions to be programmed no higher than an upper tail of the fifth threshold voltage distribution for the possible QLC logic state.

5. The memory device of claim 1, wherein the operations further comprise evenly spacing read voltage levels for each of top three possible threshold voltage distributions for the MLC logic state within a threshold percentage.

6. The memory device of claim 5, wherein a first width between each of the read voltage levels of the top three possible threshold voltage distributions is at least twice as large as a second width between each read voltage level of a corresponding QLC logic state.

7. The memory device of claim 1, wherein the particular page of the QLC logical state comprises at least one of an additional page or a lower page.

8. A method comprising: The first two bits of a particular page identifying a four-level cell QLC logic state by the memory device; causing memory cells programmed as QLC memory to be coarsely programmed with a threshold voltage distribution corresponding to the multi-level cell MLC logic states of the first two bits; reading the MLC logic state from the memory cell and reading the next two bits from a cache buffer to determine the QLC logic state; and The memory cell is further coarsely programmed with a QLC threshold voltage distribution corresponding to the QLC logic state.

9. The method of claim 8, further comprising storing only the last two bits of four bits of the QLC logic state in the cache buffer.

10. The method of claim 8, further comprising ensuring that the threshold voltage distribution is programmed to a fifth threshold voltage distribution no higher than a possible QLC logic state.

11. The method of claim 10, wherein the ensuring comprises forcing an upper tail of a highest of possible MLC threshold voltage distributions to be programmed no higher than an upper tail of the fifth threshold voltage distribution of the possible QLC logic state.

12. The method of claim 8, further comprising evenly spacing read voltage levels for each of top three possible threshold voltage distributions for the MLC logic states within a threshold percentage.

13. The method of claim 12, wherein a first width between each of the read voltage levels of the top three possible threshold voltage distributions is at least twice as large as a second width between each read voltage level of a corresponding QLC logic state.

14. The method of claim 8, wherein the particular page of the QLC logical state comprises at least one of an additional page or a lower page.

15. A computer-readable storage medium storing instructions that, when executed by a processing device of a memory subsystem, cause the processing device to perform operations comprising: The first two bits that identify a particular page of four-level cell QLC logic states; causing memory cells programmed as QLC memory to be coarsely programmed with a threshold voltage distribution corresponding to the multi-level cell MLC logic states of the first two bits; reading the MLC logic state from the memory cell and reading the next two bits from a cache buffer to determine the QLC logic state; and The memory cell is further coarsely programmed with a QLC threshold voltage distribution corresponding to the QLC logic state.

16. The computer-readable storage medium of claim 15, wherein the operations further comprise storing only the last two bits of four bits of the QLC logic state in the cache buffer.

17. The computer-readable storage medium of claim 15, wherein the operations further comprise ensuring that the threshold voltage distribution is programmed to a fifth threshold voltage distribution no higher than a possible QLC logic state.

18. The computer-readable storage medium of claim 15, wherein the operations further comprise evenly spacing read voltage levels for each of top three possible threshold voltage distributions for the MLC logic state within a threshold percentage.

19. The computer-readable storage medium of claim 18, wherein a first width between each of the read voltage levels of the top three possible threshold voltage distributions is at least twice as large as a second width between each read voltage level of a corresponding QLC logic state.

20. The computer-readable storage medium of claim 15, wherein the particular page of the QLC logical state comprises at least one of an additional page or a lower page.