Method of operating a memory device and a memory system including a memory device
By introducing a status check time setting unit into the memory system, the start time of the status check for word lines is dynamically adjusted, which solves the problem of unstable programming response time, ensures QoS in garbage collection mode, and improves data storage efficiency and system stability.
Patent Information
- Application Number
- CN202211067481.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2021-10-01
- Filing Date
- 2022-09-01
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2042-09-01
AI Technical Summary
Existing memory systems struggle to maintain a constant programming response time during garbage collection, leading to degraded Quality of Service (QoS). Furthermore, word line status check time cannot be dynamically adjusted, impacting data storage efficiency.
By introducing a status check time setting unit into the memory system, the status check start time of the word line is dynamically adjusted based on the usage of the write buffer and the maximum and minimum programming times of the word line, and a timeout signal is generated to check the busy or ready state of the word line, ensuring the stability of the programming response time.
It achieves constant programming response time under garbage collection conditions, prevents quality of service (QoS) degradation, and improves data storage efficiency and system stability.
Smart Images

Figure CN115938460B_ABST
Abstract
Description
[0001] Cross-references to related applications
[0002] This application claims priority to Korean Patent Application No. 10-2021-0130562, filed on October 1, 2021, the disclosure of which is incorporated herein by reference in its entirety. Technical Field
[0003] One or more embodiments described herein relate to a memory device and a method of operating a memory system including the memory device. Background Technology
[0004] The use of mobile phones, digital cameras, laptops, and other portable electronic devices continues to increase globally. These devices use or include memory systems, which include at least one memory device (or other data storage device).
[0005] Unlike hard drives, data storage devices implemented with non-volatile semiconductor memory offer superior stability and durability due to the absence of mechanically driven components (e.g., robotic arms). These devices also feature high data access speeds and low power consumption. Examples of such data storage devices include Universal Serial Bus (USB) memory devices, memory cards with various interfaces, and solid-state drives (SSDs). Summary of the Invention
[0006] Various embodiments of this disclosure relate to a memory system capable of dynamically adjusting the start time of word line state checks of a memory device, and a method of operating the memory system.
[0007] Furthermore, various embodiments of this disclosure relate to a memory system and a method of operating the memory system that can dynamically adjust the state check start time of the word line of the memory device based on the amount of write buffer usage and the maximum and minimum programming times of the word line.
[0008] Furthermore, various embodiments of this disclosure relate to a memory system that prevents quality of service (QoS) degradation by maintaining a constant programmed response time even when garbage collection is being performed, and a method of operating the memory system.
[0009] According to an embodiment of the present invention, a memory system may include: a memory device including at least one word line and at least one memory cell coupled to the word line; and a controller including a write buffer configured to store programming commands and data received from a host, the controller being adapted to control programming operations that store data in the word line based on programming commands, setting a status check time for the word line during the execution of the programming operations, and checking the status of the word line according to a timeout signal generated based on the set status check time.
[0010] According to an embodiment of the present invention, a method for operating a memory system may include: performing a programming operation on at least one word line; setting a state check time for the word line during the execution of the programming operation; generating a timeout signal based on the state check time; and checking the state of the word line according to the timeout signal.
[0011] According to an embodiment of the present invention, a memory system may include: a memory device including at least one memory cell coupled to at least one word line; and a controller configured to perform a programming operation on the memory cell, determine a status check time for the word line, generate a timeout signal based on the status check time, and transmit a status check command to the memory device in response to the timeout signal, causing the memory device to check the busy or ready state of the word line associated with the programming operation on the memory cell and notify the controller of the word line status. The status check time may be determined based on the sum of a basic status check time and an additional status check time. The basic status check time may be determined based on the memory cell. The additional status check time may be determined based on the target programming response time, the maximum programming time of the word line, and the minimum programming time. Attached Figure Description
[0012] Figure 1 An embodiment of a data processing system including a memory system is shown.
[0013] Figure 2 An embodiment of the memory device is shown.
[0014] Figure 3 An embodiment of the cell array circuit is shown.
[0015] Figure 4 An embodiment of the memory device structure is shown.
[0016] Figure 5 The proposed memory system is shown.
[0017] Figure 6 An example of a status check operation is shown.
[0018] Figure 7 An embodiment of the memory system is shown.
[0019] Figure 8 An example of the status check time setting process is shown.
[0020] Figure 9 An example of the status check time setting process is shown.
[0021] Figure 10 An embodiment of the data processing system is shown.
[0022] Figure 11 An embodiment of the data processing system is shown.
[0023] Figure 12 An embodiment of the data processing system is shown.
[0024] Figure 13 An embodiment of the data processing system is shown.
[0025] Figures 14 to 17 An embodiment of the data processing system is shown.
[0026] Figure 18 An embodiment of the data processing system is shown. Detailed Implementation
[0027] Various embodiments of the present disclosure are described below with reference to the accompanying drawings. However, the elements and features of the present disclosure may be configured or arranged differently to form other embodiments, which may be variations of any of the disclosed embodiments.
[0028] In this disclosure, references to various features (e.g., elements, structures, modules, components, steps, operations, characteristics, etc.) included in terms such as “one embodiment,” “example embodiment,” “embodiment,” “another embodiment,” “some embodiments,” “various embodiments,” “other embodiments,” “optional embodiments,” etc., are intended to indicate that any such feature is included in one or more embodiments of this disclosure, but may or may not be combined in the same embodiment.
[0029] In this disclosure, the terms “comprising,” “including,” “including,” and “comprising” are open-ended. As used in the appended claims, these terms specify the presence of the stated element and do not exclude the presence or addition of one or more other elements. Terms in the claims do not exclude the device from including additional components (e.g., interface units, circuitry, etc.).
[0030] In this disclosure, various units, circuits, or other components may be described or claimed as being "configured to" perform one or more tasks. In such context, "configured to" is used to indicate a structure by indicating that a block / unit / circuit / component includes a structure (e.g., a circuit) that performs one or more tasks during operation. Thus, even when a specified block / unit / circuit / component is not currently operating (e.g., not turned on or activated), it can be said that the block / unit / circuit / component is configured to perform a task. Blocks / units / circuits / components used with the language "configured to" include hardware, such as circuits, memory storing program instructions operable to perform the operation, etc. Furthermore, "configured to" may include general structures (e.g., general-purpose circuits) that are manipulated by software and / or firmware (e.g., an FPGA or a general-purpose processor running software) to perform a task to be solved. "Configured to" may also include means (e.g., integrated circuits) that adjust manufacturing processes (e.g., semiconductor manufacturing facilities) to manufacture means for implementing or performing one or more tasks.
[0031] As used in this disclosure, the term "circuit" or "logic" means all of the following: (a) a purely hardware circuit implementation (such as an implementation in analog and / or digital circuits only) and (b) a combination of circuitry and software (and / or firmware), such as (if applicable): (i) a combination of processors, or (ii) a portion of a processor / software (including digital signal processors, software, and memory that work together to enable a device such as a mobile phone or server to perform various functions), and (c) a circuitry requiring software or firmware for operation, such as a microprocessor or a portion of a microprocessor, even if the software or firmware does not actually exist. This definition of "circuit" or "logic" applies to all uses of the term in this application, including in any claim. As a further example, as used in this application, the term "circuit" or "logic" also covers implementations of only one processor (or multiple processors) or a portion of a processor and its (or their) accompanying software and / or firmware. Where applicable to a particularly stated element, the term "circuit" or "logic" also covers integrated circuits for storage devices.
[0032] When used herein, the terms “first,” “second,” “third,” etc., serve as labels for nouns following the term and do not indicate any type of ordering (e.g., spatial, temporal, logical, etc.). The terms “first” and “second” do not necessarily mean that the first value must precede the second. Furthermore, while the terms can be used to identify various components, these components are not limited by these terms. These terms are used to distinguish one component from another that would otherwise have the same or similar name. For example, a first circuit can be distinguished from a second circuit.
[0033] Furthermore, the term "based on" is used to describe one or more factors that influence the determination. This term does not exclude additional factors that may influence the determination. That is, the determination may be based solely on those factors or at least partially on those factors. For example, the phrase "A is determined based on B." Although B is a factor influencing the determination of A in this case, this phrase does not exclude the possibility that the determination of A is also based on C. In other cases, A may be determined solely based on B.
[0034] In this document, a data item, data entry, or data term can be a sequence of bits. For example, a data item may include the contents of a file, a portion of a file, a page in memory, an object in an object-oriented program, a digital message, a digitally scanned image, a portion of a video or audio signal, metadata, or any other entity that can be represented by a series of bits. According to an embodiment, a data item may include discrete objects. According to another embodiment, a data item may include information units within a data packet transmitted between two different components.
[0035] Figure 1 This is a schematic diagram illustrating an embodiment of a data processing system 100 including a memory system.
[0036] Reference Figure 1 The data processing system 100 may include a host 102 that is coupled to or operatively connected to the memory system 110.
[0037] The host device 102 may include portable electronic devices such as mobile phones, MP3 players, and laptop computers, or non-portable electronic devices such as desktop computers, game consoles, televisions (TVs), and projectors.
[0038] The host 102 includes at least one operating system (OS) for managing and controlling the functions and operations performed within the host 102. The OS can provide interoperability between the host 102, which is coupled to the memory system 110, and the user using the memory system 110. The OS can support functions and operations corresponding to user requests.
[0039] As an example and not a limitation, the OS can be categorized into general-purpose operating systems and mobile operating systems based on the mobility of host 102. Depending on, for example, system requirements or user environment, a general-purpose operating system can include personal operating systems and enterprise operating systems. A personal operating system (e.g., Windows, Chrome, etc.) can be used to support general-purpose services. In one embodiment, an enterprise operating system can be specifically designed to achieve and support high performance, including Windows servers, Linux, Unix, etc.
[0040] The mobile operating system may include Android, iOS, Windows Mobile, or other types of mobile operating systems. The mobile operating system may be used to support services or functions for mobility (e.g., power-saving features). Host 102 may include multiple operating systems and may run multiple operating systems interlocked with memory system 110, such as those corresponding to user requests. Host 102 may transmit multiple commands corresponding to user requests to memory system 110, thereby executing operations corresponding to the commands within memory system 110.
[0041] The storage device of the memory system 110 may be implemented using volatile memory devices (e.g., dynamic random access memory (DRAM), static RAM (SRAM)) and / or non-volatile memory devices (e.g., read-only memory (ROM), mask ROM (MROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), ferroelectric RAM (FRAM), phase-change RAM (PRAM), magnetoresistive RAM (MRAM), resistive RAM (RRAM or ReRAM), flash memory, etc.).
[0042] The memory system 110 may include a controller 130 and a memory device 150. The memory device 150 may store data to be accessed by the host 102. The controller 130 may control operations including storing data in the memory device 150.
[0043] The controller 130 and memory device 150 included in the memory system 110 can be integrated into a single semiconductor device, which can include any of the various types of memory systems discussed in the examples above.
[0044] By way of example and not limitation, controller 130 and memory device 150 can be implemented using an SSD. When memory system 110 is used as an SSD, the operating speed of host 102 connected to memory system 110 can be significantly higher than the operating speed of host 102 implemented using a hard disk. Alternatively, controller 130 and memory device 150 can be integrated into a single semiconductor device to form a memory card. Examples include PC cards (PCMCIA), compact flash memory (CF) cards, memory cards such as smart media cards (SM, SMC), memory sticks, multimedia cards (MMC, RS-MMC, micro MMC), SD cards (SD, mini SD, micro SD, SDHC), general-purpose flash memory, etc.
[0045] The memory system 110 can be configured as a component of, for example, a computer, an ultra-mobile PC (UMPC), a workstation, a netbook, a personal digital assistant (PDA), a portable computer, a network tablet, a tablet computer, a wireless telephone, a mobile phone, a smartphone, an e-book reader, a portable multimedia player (PMP), a portable game console, a navigation system, a black box, a digital camera, a digital multimedia broadcast (DMB) player, a three-dimensional (3D) television, a smart television, a digital audio recorder, a digital audio player, a digital picture recorder, a digital picture player, a digital video recorder, a digital video player, a storage device configured for a data center, a device capable of transmitting and receiving information in a wireless environment, one of various electronic devices configured for a home network, one of various electronic devices configured for a computer network, one of various electronic devices configured for a telematics network, a radio frequency identification (RFID) device, or one of various components configured for a computing system.
[0046] Memory device 150 may be a non-volatile memory device, and can retain the data stored therein even when power is not supplied. Memory device 150 can store data provided by host 102 via write operations, and can provide the stored data to host 102 via read operations. Memory device 150 may include a plurality of memory blocks 152, 154, 156, each of which may include a plurality of pages. Each of the plurality of pages may include a plurality of memory cells connected to a corresponding word line (WL). Memory device 150 also includes a plurality of memory dies, each of which includes a plurality of planes. Each of the plurality of planes includes some of the memory blocks among memory blocks 152, 154, 156. In addition, memory device 150 may be flash memory, for example, flash memory may have a three-dimensional stacked structure.
[0047] The controller 130 in the memory system 110 can control the memory device 150 in response to a request from the host 102. For example, the controller 130 can provide data read from the memory device 150 to the host 102 and store the data provided by the host 102 in the memory device 150. The controller 130 can control read operations, write operations, programming operations, and erase operations of the memory device 150.
[0048] The controller 130 may include a host interface 132, a processor 134, an error correction code (ECC) component 138, a power management unit (PMU) 140, a memory interface 142, and a memory 144.
[0049] Host interface 132 can process commands and data provided by host 102 and can communicate with host 102 via at least one of various interface protocols. Examples include Universal Serial Bus (USB), Multimedia Card (MMC), High-Speed Peripheral Component Interconnect (PCI-e or PCIe), Small Computer System Interface (SCSI), Serial SCSI (SAS), Serial Advanced Technology Attachment (SATA), Parallel Advanced Technology Attachment (PATA), Enhanced Small Disk Interface (ESDI), and Electronic Integrated Drive (IDE). According to an embodiment, host interface 150 can exchange data with host 102, which can be implemented via firmware such as the Host Interface Layer (HIL).
[0050] The Flash Translation Layer (FTL) unit 40 can control the general operation of the memory system 110. For example, the FTL unit 40 can receive read commands, programming commands, and logical addresses of data corresponding to the read commands and programming commands from the host interface 132, and may include a logic-to-physical (L2P) mapping to translate the logical addresses of the received data into physical addresses of the memory device 150. In one embodiment, the FTL unit 40 may be firmware driven by the processor 134.
[0051] FTL unit 40 can translate the logical address of data provided by host interface 132 into the physical address of memory device 150 corresponding to the logical address of the data. FTL unit 40 can use L2P mapping to perform this operation and can transfer the physical address of the data to memory interface 142.
[0052] FTL unit 40 may include ECC component 138, which corrects for error bits in data to be processed in memory device 150 (e.g., output from memory device). In one embodiment, ECC component 138 may include an ECC encoder and an ECC decoder. The ECC encoder may perform error-correcting encoding on the data to be programmed into memory device 150 to generate encoded data with parity bits added. The ECC encoder may then store the encoded data in memory device 150. When controller 130 reads data stored in memory device 150, ECC decoder may detect and correct errors contained in the data read from memory device 150. For example, after performing error-correcting decoding on the data read from memory device 150, ECC component 138 may determine whether the error-correcting decoding was successful and may output a command signal (e.g., a correction success signal or a correction failure signal). ECC component 138 may use parity bits (generated during the ECC encoding process) to correct for error bits in the read data. When the number of error bits is greater than or equal to the threshold number of correctable error bits, the ECC component 138 may be unable to correct the error bits, and may instead output an error correction failure signal indicating that the correction of the error bits has failed.
[0053] ECC component 138 may perform error correction operations based on coded modulation such as low-density parity-check (LDPC) codes, Bose-Chaudhuri-Hocquenghem (BCH) codes, turbo codes, Reed-Solomon (RS) codes, convolutional codes, recursive systematic codes (RSC), trellis-coded modulation (TCM), block-coded modulation (BCM), etc. ECC component 138 may include any and all circuits, modules, systems, or devices that perform error correction operations based on at least one of the codes described above.
[0054] PMU 140 can manage the power supplied by controller 130.
[0055] Memory interface 142 can serve as an interface for processing commands and data transferred between controller 130 and memory device 150, allowing controller 130 to control memory device 150 in response to requests transmitted from host 102. When memory device 150 is flash memory, specifically NAND flash memory, memory interface 142 can generate control signals for memory device 150 and can process data input to or output from memory device 150 under the control of processor 134. Memory interface 142 can provide an interface for processing commands and data between controller 130 and memory device 150, for example, for NAND flash interface operations, and particularly for operations between controller 130 and memory device 150. According to an embodiment, memory interface 142 can be implemented using firmware called a flash interface layer (FIL) as a component for exchanging data with memory device 150.
[0056] Memory 144 can support operations performed by memory system 110 and controller 130. Memory 144 can store temporary or transactional data generated or transferred due to operations in memory system 110 and controller 130. Controller 130 can control memory device 150 in response to requests from host 102. Controller 130 can transfer data read from memory device 150 to host 102. Controller 130 can store data input through host 102 within memory device 150. Memory 144 can be used to store data for controller 130 and memory device 150 to perform operations such as read operations, programming / write operations, or erase operations.
[0057] When the controller 130 controls the read, write, program, and erase operations of the memory device 150, the data transferred or generated between the controller 130 and the memory device 150 in the memory system 110 can be stored in the memory 144. For example, the memory 144 can store data used to perform data write and read operations between the host 102 and the memory device 150, as well as data during the execution of data write and read operations. For such data storage, the memory 144 may include program memory, data memory, write buffer / cache, read buffer / cache, data buffer / cache, mapping buffer / cache, etc.
[0058] Memory 144 may be volatile memory or may include volatile memory. For example, memory 144 may be static random access memory (SRAM) or dynamic random access memory (DRAM), or may include static random access memory (SRAM) or dynamic random access memory (DRAM). As shown, memory 144 may reside inside controller 130. In one embodiment, memory 144 may reside outside controller 130. In this case, memory 144 may be external volatile memory or may include external volatile memory, with data input to and output from the external volatile memory to controller 130 via a separate memory interface.
[0059] Processor 134 controls all operations of memory system 110. For example, processor 134 controls programming or reading operations on memory device 150 in response to write or read requests from host 102. Processor 134 drives firmware (e.g., flash translation layer (FTL)) to control the general operation of memory system 110. Processor 134 can be implemented using a microprocessor or a central processing unit (CPU).
[0060] For example, controller 130 performs operations in memory device 150 according to a request from host 102. In one embodiment, controller 130 uses memory device 150 to execute command operations (corresponding to commands received from host 102) via processor 134 implemented by a microprocessor or central processing unit (CPU). Controller 130 may perform foreground operations, such as command operations corresponding to commands received from host 102. In one embodiment, controller 130 may perform programming operations corresponding to write commands, reading operations corresponding to read commands, erasing operations corresponding to erase commands, or parameter setting operations corresponding to setting parameter commands or setting feature commands as setting commands.
[0061] The controller 130 can also perform background operations on the memory device 150 via a processor 134 implemented by a microprocessor or a central processing unit (CPU). Background operations on the memory device 150 may include copying data stored in one of the memory blocks 152, 154, and 156 of the memory device 150 to another memory block, such as a garbage collection (GC) operation. Background operations may exchange data between one or more of the memory blocks 152, 154, and 156 of the memory device 150, such as a wear leveling (WL) operation and a read recovery (RR) operation. Background operations may store mapped data retrieved from the controller 130 in the memory blocks 152, 154, and 156 of the memory device 150, such as a map clearing operation. Background operations may include bad block management operations on the memory device 150, which may include checking and processing bad blocks in the plurality of memory blocks 152, 154, and 156 of the memory device 150.
[0062] Controller 130 executes multiple command operations corresponding to multiple commands from host 102. For example, when executing multiple read operations corresponding to multiple read commands and multiple erase operations corresponding to multiple erase commands sequentially, randomly, or alternately, controller 130 can determine which of a plurality of channels or paths connecting controller 130 to multiple memory dies in memory device 150 is suitable or applicable for executing each operation. Controller 130 can transmit data or instructions via the determined channel or path for executing each operation. Memory dies in memory device 150 can transmit operation results separately via the same channel or path after each operation is completed. Controller 130 can then transmit a response or acknowledgment signal to host 102. In an embodiment, controller 130 can check the status of each channel or path. In response to a command from host 102, controller 130 can select at least one channel or path based on the status of each channel or path, thereby enabling the transmission of instructions and / or operation results and data via the selected channel or path.
[0063] By way of example and not limitation, controller 130 may identify the status of multiple channels (or pathways) associated with multiple memory dies in memory device 150. For example, controller 130 may determine each channel or pathway as one of a busy state, a ready state, an active state, an idle state, a normal state, and / or an abnormal state. The determination by controller 130 may be associated with physical block addresses. Controller 130 may reference descriptors from memory device 150. For example, the descriptor may include parameters describing one or more characteristics of memory device 150. In one embodiment, the descriptor may be data with a defined format or structure. For example, the descriptor may include a device descriptor, a configuration descriptor, and / or a cell descriptor. Controller 130 may refer to or use the descriptors to determine via which channel(s) or pathways instructions or data are exchanged.
[0064] The status check time setting unit 510 can be set to perform a status check after the memory device 150 begins programming a word line. For example, the status check time can instruct the controller 130 to begin performing a status check after programming begins. In one embodiment, when the programming execution time for any word line of the memory device 150 is a predetermined time (e.g., 1500 µs), the status check time setting unit 510 can set the status check time to 1500 µs so that a status check is performed on the word line after 1500 µs. In this case, the status check time setting unit 510 can check whether the programming command has been transmitted to the memory device 150, set the status check time, or not set the status check time if the programming command has not yet been transmitted to the memory device 150.
[0065] The timeout generation unit 520 can generate a timeout signal when the state check time set by the state check time setting unit 510 has elapsed, and transmit the generated timeout signal to the state check execution unit 530. For example, when the state check time set by the state check time setting unit 510 is a predetermined time (e.g., 1500us), the timeout generation unit 520 can generate a timeout signal after 1500us and transmit the generated timeout signal to the state check execution unit 530. In another embodiment, the predetermined time may be different from 1500us.
[0066] The status check execution unit 530 can check the status of the word line that has been programmed based on the timeout signal received from the timeout generation unit 520. Examples of word line statuses can include a ready state where other commands are executable and a busy state where other commands are not executable.
[0067] For example, when the status check execution unit 530 receives a timeout signal and checks the status of the word line while the memory device 150 is still performing word line programming, the status check execution unit 530 can receive a signal from the memory device 150 indicating that the word line is in a busy state. When the memory device 150 completes the word line programming, the word line status can change from a busy state to a ready state, and the status check execution unit 530 can receive a signal from the memory device 150 indicating that the word line is in a ready state.
[0068] The status check execution unit 530 can perform status checks on word lines that are being programmed or have already been programmed at specific time intervals or a specific number of times. The status check execution unit 530 can change the specific time interval or the specific number of times based on the characteristics or type of the word line.
[0069] The status check time setting unit 510, the timeout generation unit 520, and the status check execution unit 530 can be hardware modules or software modules executed by the processor 134.
[0070] Reference Figures 2 to 4 A detailed description of an embodiment of the memory device in the memory system.
[0071] Figure 2 This is a schematic diagram illustrating an embodiment of a memory device. Figure 3 This is a schematic diagram illustrating an embodiment of a cell array circuit of memory blocks in a memory device. Figure 4 This is a schematic diagram illustrating an embodiment of a memory device structure in a memory system.
[0072] Reference Figure 2 The memory device 150 may include a plurality of memory blocks BLOCK 0 to BLOCK N-1, where N is an integer greater than 1. Each of the blocks BLOCK 0 to BLOCK N-1 may include a plurality of pages, for example 2 M There may be M pages, the number of which can vary depending on the circuit design, and M is an integer greater than 1. Each of the multiple pages may include multiple memory cells connected to multiple word lines WL.
[0073] The memory cells in each of the memory blocks BLOCK 0 to BLOCK N-1 can be one or more of a single-level cell (SLC) storing 1 bit of data or a multi-level cell (MLC) storing 2 bits of data. Therefore, depending on the number of bits in each of the memory cells that can be represented or stored in the memory block, the memory device 150 can include a memory block containing SLC (e.g., an SLC memory block) or a memory block containing MLC (e.g., an MLC memory block). An SLC memory block can include multiple pages implemented by memory cells that each store one bit of data. SLC memory blocks typically offer higher data processing performance and greater durability than MLC memory blocks. An MLC memory block can include multiple pages implemented by memory cells that each store multiple bits of data (e.g., 2 or more bits). MLC memory blocks typically offer larger data storage space (e.g., higher integration density) than SLC memory blocks.
[0074] In another embodiment, the memory device 150 may include a plurality of three-level cell (TLC) memory blocks. A TLC memory block may include multiple pages, each implemented by a memory cell capable of storing 3 bits of data. In another embodiment, the memory device 150 may include a plurality of four-level cell (QLC) memory blocks. A QLC memory block may include multiple pages, each implemented by a memory cell capable of storing 4 bits of data.
[0075] In addition to non-volatile memory, including NAND flash memory, memory device 150 may be implemented by any of the following: phase-change random access memory (PCRAM), resistive random access memory (RRAM or ReRAM), ferroelectric random access memory (FRAM), or spin-transfer torque magnetic random access memory (STT-RAM or STT-MRAM).
[0076] Storage blocks 152, 154, 156, and 180 can be programmed to store data transmitted from host 102, and can be read to transmit the stored data back to host 102.
[0077] Reference Figure 3A memory block 330, representing any one of the memory blocks in memory device 150, may include multiple cell strings 340 connected to multiple corresponding bit lines BL0 to BLm-1. Each cell string 340 may include one or more drain-select transistors (DSTs) and one or more source-select transistors (SSTs). Multiple memory cells MC0 to MCn-1 may be connected in series between the drain-select transistors (DSTs) and the source-select transistors (SSTs). In an embodiment, each of the memory cell transistors MC0 to MCn-1 may be implemented by an MLC capable of storing multiple bits of data. Each of the cell strings 340 may be electrically connected to a corresponding bit line among the bit lines BL0 to BLm-1. For example, as Figure 3 As shown, the first cell is connected in series to the first bit line BL0, and the last cell is connected in series to the last bit line BLm-1.
[0078] although Figure 3 NAND flash memory cells are shown, but the invention is not limited thereto. Note that the memory cells may be NOR flash memory cells, or may include hybrid flash memory cells that combine two or more types of memory cells. In one embodiment, memory device 150 may be a flash memory device including a conductive floating gate as a charge storage layer or a charge-fetch flash memory (CTF) device including an insulating layer as a charge storage layer.
[0079] The memory device 150 may further include a voltage supply unit 310, which generates different word line voltages supplied to the word lines according to the operating mode, such as programming voltage, read voltage, and pass voltage. The voltage generation operation of the voltage supply unit 310 can be controlled by a control circuit. Under the control of the control circuit, the voltage supply unit 310 can select at least one memory block (or sector) of the memory cell array, select at least one word line of the selected memory block, and provide word line voltages to the selected word lines and unselected word lines as needed.
[0080] Memory device 150 may include read / write circuitry 320 controlled by control circuitry. During verification / normal read operations, read / write circuitry 320 may operate as a readout amplifier for reading (sensing and amplifying) data from the memory cell array. During programming operations, read / write circuitry 320 may operate as a write driver for supplying voltage or current to bit lines based on the data to be stored in the memory cell array. During programming operations, read / write circuitry 320 may receive data to be stored in the memory cell array from a buffer and drive bit lines based on the received data. Read / write circuitry 320 may include a plurality of page buffers (PB) 322 to 326 corresponding to columns (or bit lines) or column pairs (or bit line pairs), respectively. Each of page buffers 322 to 326 may include a plurality of latches.
[0081] The memory device 150 can be implemented as a two-dimensional (2D) or three-dimensional (3D) memory device. Specifically, such as... Figure 4 As shown, the memory device 150 can be implemented by a non-volatile memory device having a 3D stacked structure. When the memory device 150 has a 3D structure, the memory device 150 can include multiple memory blocks BLK0 to BLKN-1. Figure 4 In the middle, the block diagram shows Figure 1 The memory device 150 shown includes memory blocks 152, 154, and 156. Each of memory blocks 152, 154, and 156 can be implemented as a 3D structure (or a vertical structure). For example, each of memory blocks 152, 154, and 156 can be a 3D structure having dimensions extending from a first direction to a third direction (e.g., the x-axis, y-axis, and z-axis directions).
[0082] Each memory block 330 in the memory device 150 may include a plurality of NAND strings NS extending in a second direction. The plurality of NAND strings NS extend upward in a first direction and a third direction. In one embodiment, each of the NAND strings NS may be coupled to a bit line BL, at least one string select line SSL, at least one ground select line GSL, multiple word lines WL, at least one dummy word line DWL, and a common source line CSL. For example, each of the NAND strings NS may include a plurality of transistor structures TS.
[0083] Therefore, in memory blocks 152, 154, and 156 of memory device 150, each memory block 330 can be connected to multiple bit lines BL, multiple string select lines SSL, multiple ground select lines GSL, multiple word lines WL, multiple dummy word lines DWL, and multiple common source lines CSL, and each memory block 330 can include multiple NAND strings NS. In each memory block 330, a bit line BL can be connected to multiple NAND strings NS to implement multiple transistors in one NAND string NS. The string select transistor SST of each NAND string NS can be connected to the corresponding bit line BL, and the ground select transistor GST of each NAND string NS can be connected to the common source line CSL. Memory cells MC can be disposed between the string select transistor SST and the ground select transistor GST of each NAND string NS. For example, multiple memory cells can be implemented in each memory block 330 of memory blocks 152, 154, and 156 of memory device 150.
[0084] Figure 5 This is a diagram illustrating a memory system that may include some of the reference numerals mentioned above.
[0085] Reference Figure 5 The memory device 150 can perform erase, write, and read operations under the control of the controller 130. The memory device 150 can receive commands (CMD), addresses (ADDR), and data (DATA) from the controller 130 via input / output lines. Commands (CMD) may include read commands for performing read operations, write commands for performing programming operations, and status check commands for performing status checks on word lines.
[0086] Additionally, the memory device 150 can receive power PWR from the controller 130 via a power line and control signals CTRL from the controller 130 via a control line. The control signals CTRL may include a data strobe signal DQS, a command latch enable signal CLE, an address latch enable signal ALE, a chip enable signal CE, a write enable signal WE, and a read enable signal RE.
[0087] The memory device 150 may include a cell array 330, a control circuit 360, a voltage supply unit 310, a voltage transmission unit 390, a read / write circuit 320, and a column selection unit 380.
[0088] The cell array 330 may include multiple storage blocks 350. User data may be stored in the storage blocks 350.
[0089] The control circuit 360 can control general operations related to programming, erasing and reading operations of the memory device 150.
[0090] The voltage supply unit 310 can generate word line voltages to be supplied to each word line according to the operating mode, such as programming voltage, read voltage, and pass voltage, as well as voltages to be supplied to a bulk, such as a well region containing memory cells. The voltage generation operation of the voltage supply unit 310 can be performed under the control of the control circuit 360.
[0091] The voltage supply unit 310 can generate multiple variable read voltages or programming voltages to read data from the storage block 350 or program data into the storage block 350.
[0092] The voltage transmission unit 390 can select one of the memory blocks or sectors in the cell array 330 in response to the control of the control circuit 360, and select one of the word lines of the selected memory block. The voltage transmission unit 390 can also supply the word line voltage generated by the voltage supply unit 310 to the selected word line and the unselected word line in response to the control of the control circuit 360.
[0093] The read / write circuit 320 can be controlled by the control circuit 360 and operates as a read amplifier or a write driver depending on the operating mode. For example, in the case of a verification / normal read operation, the read / write circuit 320 can operate as a read amplifier for reading data from the cell array 330. During a normal read operation, the column selection unit 380 can output the data read from the read / write circuit 320 to an external device, such as a controller, in response to column address information. Unlike this configuration, during a verification read operation, the read data can be provided to the pass / fail verification circuitry included in the memory device 150 and used to determine whether the memory cell has been successfully programmed.
[0094] In the case of programming operation, the read / write circuit 320 can operate as a write driver for driving bit lines according to the data to be stored in the cell array 330. During programming operation, the read / write circuit 320 can receive data to be written to the cell array 330 from the buffer of the controller 130 and drive the bit lines according to the input data.
[0095] For this purpose, the read / write circuitry 320 may include multiple page buffers, each corresponding to a column (or bit line) or column pair (or bit line pair). Multiple latches may be included in each of the page buffers. Each of the page buffers may include a most significant bit (MSB) page buffer, a middle significant bit (CSB) page buffer, and a least significant bit (LSB) page buffer.
[0096] In the case of a status check operation, the read / write circuit 320 can check whether the programming operation on the word line has been completed. The read / write circuit 320 can notify the control circuit 360 that the word line is busy while the programming operation on the word line is being performed, and notify the control circuit 360 that the word line is ready when the programming operation on the word line has been completed. The control circuit 360 can also notify the controller 130 of the status of the word line.
[0097] Figure 6 This is a diagram illustrating an embodiment of a status check operation, wherein programming is performed on word lines. (Refer to...) Figure 6 During the Data IN period of input data, the controller 130 can transfer the data to be programmed to the memory device 150, and the read / write circuit 320 can receive the data to be programmed.
[0098] Subsequently, the read / write circuit 320 can apply a programming voltage to the word line and perform programming during the programming execution cycle Program. Programming is performed within the programming execution time tPROG. The controller 130 can transmit programming commands to the memory device 150 and set a status check time. The status check time can be calculated from the start of programming until the end of programming. When the status check time has elapsed, the controller 130 can transmit a status check command to the memory device 150 to check the busy / ready state of the word line. The control circuit 360 can check the state of the word line according to the received status check command and can transmit the status check result of the word line to the controller 130.
[0099] If the programming of the word line is not finished, the memory device 150 may notify the controller 130 that the word line is busy. In this case, the controller 130 may continue to perform the status check operation at a predetermined period or a predetermined number of times until the programming of the word line is finished, the word line status becomes ready, and the status check is completed.
[0100] Since the status check is based on the word line programming execution time tPROG, the programming response time (e.g., the time it takes for host 102 to transmit a command to controller 130 and then receive a response to the command from controller 130) can be proportional to the time from when the word line programming is completed and the controller 130 is notified of the word line's status until the word line's status changes to a ready state. This time can vary depending on the characteristics of the word line.
[0101] Programming response time, which varies depending on the word line, can affect Quality of Service (QoS). In situations where garbage collection is performed due to insufficient free blocks in memory device 150, a constant response time to commands (e.g., a constant programming response time) may be a more significant factor in QoS than the number of command processing operations per second. Furthermore, a non-constant programming response time can degrade QoS.
[0102] Figure 7 It shows that it can be used with Figure 5 A block diagram of an embodiment of a memory system 110, which is substantially the same as a memory device 150.
[0103] Reference Figure 7 The controller 130 may include a status check time setting unit 510, a timeout generation unit 520, a status check execution unit 530, and a write buffer 544.
[0104] The status check time setting unit 510 can calculate the time required to perform a status check on a word line after the memory device 150 begins programming the word line. For example, it can calculate the time required to perform a check to determine whether the word line is in a ready state because programming has been fully completed or in a busy state because programming is currently being performed on the word line. Furthermore, the status check time setting unit 510 can transmit the status check time to the timeout generation unit 520, causing the timeout generation unit 520 to set the status check time.
[0105] The status check time setting unit 510 can calculate the status check time CHK_TIME based on the basic status check time. In an embodiment, the basic status check time can be the time set for each block, plane, or die.
[0106] Additionally, the status check time setting unit 510 can calculate the status check time based on an additional status check time. In an embodiment, the additional status check time can be calculated based on the target programming response time of the memory system 110, the basic status check time, the programming time per word line, or the utilization rate of the write buffer 544.
[0107] In this embodiment, the status check time can be calculated as the sum of the basic status check time and the additional status check time. The additional status check time can refer to the time delay after the basic status check time. For example, the timeout generation unit 520 can generate a timeout signal SIG_TIMEOUT after the basic status check time has elapsed and further after the additional status check time has elapsed. Then, the timeout generation unit 520 can transmit the generated timeout signal to the status check execution unit 530. Upon receiving the timeout signal, the status check execution unit 530 can perform a status check on the word line or block. For example, the additional status check time can correspond to the time that delays the status check by the additional status check time after the basic status check time has elapsed.
[0108] The additional status check time for each word line or each block can be calculated, and the status check execution unit 530 can perform status checks on the word lines after the basic status check time and further after the additional status check time. In this case, the programming response time can remain constant compared to the case where the status check execution unit 530 performs status checks only after the basic status check time, which allows for improved Quality of Service (QoS).
[0109] The controller 130 may use part or all of the memory 144 as a write buffer 544 to store data before it is programmed into the memory device 150.
[0110] The status check time setting unit 510 can calculate the additional status check time based on the difference between the maximum word line programming time and the minimum word line programming time.
[0111] Therefore, the status check time setting unit 510 can calculate the maximum word line programming time and the minimum word line programming time for each block, plane or die.
[0112] Additionally, the status check time setting unit 510 can check the utilization rate of the write buffer 544 and calculate an additional status check time that is inversely proportional to the utilization rate of the write buffer 544. The utilization rate of the write buffer 544 can be represented based on the ratio of the current utilization of the write buffer 544 to the target utilization of the write buffer 544. As the utilization rate of the write buffer 544 decreases, the additional status check time may increase.
[0113] When calculating the status check time, the status check time setting unit 510 can transmit the calculated time CHK_TIME to the timeout generation unit 520. The timeout generation unit 520 can be configured to generate a timeout signal after the status check time has elapsed from the same time programming begins from the memory device 150. Then, the timeout generation unit 520 can transmit the timeout signal SIG_TIMEOUT to the status check execution unit 530.
[0114] When a timeout signal SIG_TIMEOUT is received from the timeout generation unit 520, the status check execution unit 530 can check whether the programming of the word line has been completed. In an embodiment, the status check execution unit 530 can control the memory interface 142 such that the memory interface 142 transmits a status check command and the memory device 150 executes the status check command to notify the status of the word line associated with the programming.
[0115] The status check execution unit 530 can perform status checks before the word line programming is completed. When the word line programming is completed and the word line is in a ready state, the status check execution unit 530 can notify the processor 134 that the word line status check has been completed and the word line is in a ready state. When the word line programming is not yet completed, the status check execution unit 530 can continuously perform status checks at predetermined intervals or predetermined numbers of times.
[0116] Figure 8 A flowchart illustrating an embodiment of the status check time setting process is provided. (Refer to...) Figure 7 and Figure 8 In S810, the processor 134 can request the status check time setting unit 510 to calculate the status check time.
[0117] In S820, the status check time setting unit 510 can check whether the memory system 110 is performing a garbage collection operation. While garbage collection is in progress, whether the programming response time is constant has a greater impact on Quality of Service (QoS) in some cases than the number of programming command processing operations per second.
[0118] Therefore, even if the programming response time increases, it can be considered that keeping the programming response time constant is a more important factor in these cases.
[0119] Program execution time varies depending on the word line, therefore program response time also varies.
[0120] When there are significant deviations in the programmed response time, the Quality of Service (QoS) may be assessed as relatively low. Therefore, it is possible to maintain a constant programmed response time to preserve QoS.
[0121] Since there are a sufficient number of free blocks to be programmed when the memory system 110 is not in a garbage collection state, the programming response time is unaffected. Therefore, the controller 130 can stop setting the status check time.
[0122] In S830, the status check time setting unit 510 can check whether the write buffer 544 is full (i.e., saturated) or conversely, at a predetermined capacity. The controller 130 can use part or all of the memory 144 as the write buffer 544 to store data before programming it into the memory device 150. When the write buffer 544 is full (or at a predetermined capacity), the data in the write buffer 544 can be processed quickly, thereby reducing or minimizing the programming response time. In this case, the status check time setting unit 510 may not set the status check time.
[0123] In S840, the status check time setting unit 510 can compare the target programming response time with the basic status check time.
[0124] The target programming response time can correspond to the target time required until the memory system 110 receives a command from the host 102, executes the programming, and transmits the programming completion to the host 102. For example, the basic status check time can correspond to a predetermined status check time.
[0125] When the target programming time is greater than the basic state check time, it indicates that additional state check time is required. Therefore, the state check time setting unit 510 can continue setting the state check time. When the target programming time is equal to or less than the basic state check time, it indicates that no additional state check time is required. Therefore, the state check time setting unit 510 can stop setting the state check time. In this case, the state check time can be set to the basic state check time, or it can be set based on the programming time of each word line.
[0126] In S850, the status check time setting unit 510 can compare the difference between the target programming response time and the basic status check time with the difference between the maximum word line programming time and the minimum word line programming time. In this embodiment, when the difference between the target programming response time and the basic status check time is equal to or greater than the difference between the maximum word line programming time and the minimum word line programming time, the status check time setting unit 510 can calculate the status check time based on the difference between the target programming response time and the basic status check time. When the difference between the target programming response time and the basic status check time is less than the difference between the maximum word line programming time and the minimum word line programming time, the status check time setting unit 510 can calculate the status check time based on the difference between the maximum word line programming time and the minimum word line programming time.
[0127] For example, the status check time setting unit 510 can calculate the status check time based on the greater of the difference between the target programming response time and the basic status check time and the difference between the maximum word line programming time and the minimum word line programming time.
[0128] In S860, the status check time setting unit 510 can notify the processor 134 that the status check time calculation is complete.
[0129] In S870, processor 134 can request status check time setting unit 510 to set the status check time. At the same time, processor 134 can transmit programming commands to memory device 150 through memory interface 142.
[0130] In S890, the status check time setting unit 510 (the processor 134 has requested the status check time setting unit 510 to set the status check time) can transmit the calculated status check time to the timeout generation unit 520.
[0131] At the moment when the processor 134 transmits programming commands to the memory device 150 and the memory device 150 executes the programming commands, a timeout period equal to the status check time can be set.
[0132] In S900, the timeout generation unit 520 can check whether the timeout period has elapsed. When the timeout period has elapsed, in S910, the timeout generation unit 520 can transmit a timeout signal to the status check execution unit 530.
[0133] In S920, the status check execution unit 530 can check the status of the word lines of the memory device 150 that are being programmed or have been programmed. When the result of the status check indicates that the word line is busy, the status check execution unit 530 can continuously perform status checks at a predetermined period or a predetermined number of times.
[0134] When the result of the status check indicates that the word line is in a ready state, then in S930, the status check execution unit 530 can notify the processor 134 that the word line is in a ready state and the status check has been completed.
[0135] Figure 9 This is a flowchart illustrating an embodiment of the status check time setting process.
[0136] Reference Figure 9 In S1010, the controller 130 can check whether the memory system 110 is currently performing garbage collection.
[0137] When the memory system 110 is currently in a garbage collection state (i.e., "yes" in S1010), the controller 130 may check in S1020 whether the write buffer 544 is full (or at a predetermined capacity). When the memory system 110 is not currently in a garbage collection state (i.e., "no" in S1010), the controller 130 may terminate the setting status check time.
[0138] When the memory system 110 is currently performing a garbage collection operation, whether the programming response time is constant has a greater impact on the Quality of Service (QoS) in some cases than the number of programming command processing operations per second. Therefore, even if the programming response time increases, maintaining a constant programming response time may be a priority in some situations.
[0139] Since the memory system does not currently have a sufficient number of free blocks to be programmed while performing garbage collection, the programming response time is unaffected. Therefore, the controller 130 can stop setting the status check time.
[0140] When the write buffer 544 is not full (i.e., "No" in S1020), then in S1030, the controller 130 can compare the target programming response time with the basic state check time.
[0141] For example, the status check time can be the sum of the basic status check time and the additional status check time. The additional status check time can be determined based on the maximum word line programming time, the minimum word line programming time, and the amount of write buffer usage.
[0142] The maximum or minimum word line programming time can be the word line programming time calculated based on a block, a plane, or a die.
[0143] In this embodiment, the maximum word line programming time or the minimum word line programming time can correspond to the word line programming time calculated based on a block.
[0144] Additional status check time can be inversely proportional to write buffer utilization. For example, as write buffer utilization decreases, additional status check time may increase further, leading to increased write buffer utilization.
[0145] When the target programming response time is greater than the basic state check time (i.e., "yes" in S1030), then in S1040, the controller 130 can check whether the difference between the target programming response time and the basic state check time is less than the difference between the maximum word line programming time and the minimum word line programming time.
[0146] For example, when the difference between the target programming response time and the basic status check time is less than the difference between the maximum word line programming time and the minimum word line programming time (i.e., "yes" in S1040), the status check time can be the sum of the basic status check time and the additional status check time. For example, the additional status check time can be a value obtained by dividing the difference between the maximum word line programming time and the minimum word line programming time by the ratio of the current usage of the write buffer to the target usage of the write buffer.
[0147] In one embodiment, the state check time can be represented by Equation 1:
[0148] Status check time = Basic status check time + [(Maximum word line programming time - Minimum word line programming time) / (Current usage of write buffer / Target usage of write buffer)](1)
[0149] When the difference between the target programming response time and the basic status check time is equal to or greater than the difference between the maximum word line programming time and the minimum word line programming time (i.e., "No" in S1040), the status check time corresponds to the sum of the basic status check time and the additional status check time. Furthermore, the additional status check time can be a value obtained by dividing the difference between the target programming response time and the basic status check time by the ratio of the current usage of the write buffer to the target usage of the write buffer.
[0150] In one embodiment, the state check time can be represented by Equation 2:
[0151] Status check time = Basic status check time + [(Target programming response time - Basic status check time) / (Current usage of write buffer / Target usage of write buffer)](2)
[0152] Therefore, when the difference between the target programming response time and the basic state check time is less than the difference between the maximum word line programming time and the minimum word line programming time, the controller 130 can calculate the additional state check time based on the maximum word line programming time and the minimum word line programming time. When the difference between the target programming response time and the basic state check time is equal to or greater than the difference between the maximum word line programming time and the minimum word line programming time, the controller 130 can calculate the additional state check time based on the difference between the target programming response time and the basic state check time.
[0153] Additionally, in one embodiment, the additional state check time can be proportional to the write buffer utilization. As shown in Equations 1 and 2, the additional state check time increases to a higher level when the current utilization of the write buffer is less than the target utilization. In the case of Equation 1, when the current utilization and the target utilization of the write buffer are the same, the additional state check time can be a value obtained by subtracting the minimum word line programming time from the maximum word line programming time. When the current utilization of the write buffer is less than the target utilization, the additional state check time can be greater than the value obtained by subtracting the minimum word line programming time from the maximum word line programming time. When the current utilization of the write buffer is less than the target utilization, this means that programming the memory device 150 is faster and the response is faster compared to when the current utilization and the target utilization of the write buffer are the same. Therefore, when the current utilization of the write buffer is less than the target utilization, the additional state check time increases to a higher level compared to when the current utilization and the target utilization of the write buffer are the same.
[0154] Conversely, when the current usage of the write buffer is greater than the target usage of the write buffer, the additional state check time can be less than the value obtained by subtracting the minimum word line programming time from the maximum word line programming time. When the current usage of the write buffer is greater than the target usage of the write buffer, this means that programming the memory device 150 is performed later and the response is delayed compared to when the current usage and the target usage of the write buffer are equal. Therefore, when the current usage of the write buffer is greater than the target usage of the write buffer, the additional state check time may be reduced compared to when the current usage and the target usage of the write buffer are equal. This may mean that the additional state check time does not need to be equal to or greater than the value obtained by subtracting the minimum word line programming time from the maximum word line programming time. This is because the current usage of the write buffer will be greater than the target usage of the write buffer, and the delay in response time is as much as the difference in usage.
[0155] Equation 2 allows for the calculation of the additional state check time, similar to Equation 1. For example, when the current usage of the write buffer and the target usage of the write buffer are the same, the additional state check time can be obtained by subtracting the basic state check time from the target programmed response time. When the current usage of the write buffer is less than the target usage of the write buffer, the additional state check time can be greater than the value obtained by subtracting the basic state check time from the target programmed response time. Conversely, when the current usage of the write buffer is greater than the target usage of the write buffer, the additional state check time can be less than the value obtained by subtracting the basic state check time from the target programmed response time.
[0156] As described above, according to this embodiment, even when in a garbage collection state, the memory system 110 can maintain a constant programming response time to prevent differences between programming response times and to prevent quality of service (QoS) degradation.
[0157] In the following text, reference will be made to Figures 10 to 18 For applications that incorporate the above references according to the disclosed embodiments Figures 1 to 9 The memory system 110, which includes the memory device 150 and controller 130, is described in detail as a data processing system and electronic device.
[0158] Figure 10 This is a diagram illustrating another embodiment of a data processing system including a memory system. For example, Figure 10 An embodiment of a memory card system 6100 that can be applied to a memory system is shown.
[0159] Reference Figure 10 The memory card system 6100 may include a memory controller 6120, a memory device 6130, and a connector 6110. The memory controller 6120 may be electrically connected to the memory device 6130 implemented with non-volatile memory (NVM) and is configured to access the memory device 6130 implemented with NVM. For example, the memory controller 6120 may be configured to control read operations, write operations, erase operations, and background operations of the memory device 6130. The memory controller 6120 may be configured to provide an interface between the memory device 6130 and a host and to use firmware to control the memory device 6130. For example, the memory controller 6120 may correspond to a reference... Figure 1 The described memory system 110 includes a controller 130, and the memory device 6130 may correspond to the referenced... Figure 1 The memory device 150 of the memory system 110 described herein.
[0160] Therefore, the memory controller 6120 may include random access memory (RAM), a processor, a host interface, a memory interface, and an error correction component.
[0161] The memory controller 6120 can be connected to an external device (e.g., via connector 6110) Figure 1 Communication with host 102). For example, see reference. Figure 1 The memory controller 6120 can be configured to communicate with external devices via one or more of the following communication protocols: Universal Serial Bus (USB), Multimedia Card (MMC), Embedded MMC (eMMC), Peripheral Component Interconnect (PCI), High-Speed PCI (PCIe), Advanced Technology Attachment (ATA), Serial ATA, Parallel ATA, Small Computer System Interface (SCSI), Enhanced Small Disk Interface (EDSI), Electronic Integrated Drive (IDE), FireWire, Universal Flash Memory (UFS), Wireless Fidelity (Wi-Fi or WiFi), or Bluetooth. Therefore, the memory system and data processing system according to this embodiment can be applied to wired / wireless electronic devices or specific mobile electronic devices.
[0162] The memory device 6130 may be implemented using non-volatile memory (NVM). For example, the memory device 6130 may be implemented using any of the following non-volatile memory devices: erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), NAND flash memory, NOR flash memory, phase-change RAM (PRAM), resistive RAM (ReRAM), ferroelectric RAM (FRAM), or spin-transfer torque magnetic RAM (STT-MRAM).
[0163] The memory controller 6120 and memory device 6130 can be integrated into a single semiconductor device to form a solid-state drive (SSD). Furthermore, the memory controller 6120 and memory device 6130 can be integrated to form a memory card. Examples include PC cards (Personal Computer Memory Card International Association (PCMCIA)), compact flash (CF) cards, smart media cards (e.g., SM and SMC), memory sticks, multimedia cards (e.g., MMC, RS-MMC, micro MMC, and eMMC), secure digital (SD) cards (e.g., SD, mini SD, micro SD, and SDHC), and / or universal flash memory (UFS).
[0164] Figure 11 This is a diagram illustrating another embodiment of a data processing system 6200 including a memory system according to an embodiment.
[0165] Reference Figure 11The data processing system 6200 may include a memory device 6230 having one or more non-volatile memories (NVMs) and a memory controller 6220 for controlling the memory device 6230. See also... Figure 1 As described, Figure 11 The data processing system 6200 can be used as a storage medium such as a memory card (e.g., CF, SD, micro SD, etc.) or a USB device. The memory device 6230 can correspond to... Figure 1 The memory device 150 in the illustrated memory system 110, and the memory controller 6220 may correspond to Figure 1 The controller 130 in the memory system 110 shown.
[0166] The memory controller 6220 can control read, write, or erase operations on the memory device 6230 in response to a request from the host 6210. The memory controller 6220 may include one or more central processing units (CPUs) 6221, a buffer memory such as random access memory (RAM) 6222, error correction code (ECC) circuitry 6223, a host interface 6224, or a memory interface such as a non-volatile memory (NVM) interface 6225.
[0167] The CPU 6221 can control all operations on the memory device 6230, such as read operations, write operations, file system management operations, and bad page management operations. The RAM 6222 can operate under the control of the CPU 6221 and can be used as working memory, buffer memory, or cache memory. When the RAM 6222 is used as working memory, data processed by the CPU 6221 can be temporarily stored in the RAM 6222. When the RAM 6222 is used as buffer memory, it can buffer data transferred from the host 6210 to the memory device 6230 or vice versa. When the RAM 6222 is used as cache memory, it can assist the slower memory device 6230 in operating at a higher speed.
[0168] ECC circuit 6223 can generate error correction codes (ECCs) for correcting failure or error bits in data provided from memory device 6230. ECC circuit 6223 can perform error correction encoding on data provided to memory device 6230, thereby forming data with parity bits. Parity bits can be stored in memory device 6230. ECC circuit 6223 can perform error correction decoding on data output from memory device 6230. ECC circuit 6223 can use parity bits to correct errors. ECC circuit 6223 can correct errors based on low-density parity-check (LDDC) codes, Bose-Chaudhri-Hocquenghem (BCH) codes, turbo codes, Reed-Solomon (RS) codes, convolutional codes, recursive systematic codes (RSC), or coded modulation such as trellis-coded modulation (TCM) or block-coded modulation (BCM).
[0169] The memory controller 6220 can transmit data to / receive data from the host 6210 via the host interface 6224. The memory controller 6220 can transmit data to / receive data from the memory device 6230 via the NVM interface 6225. The host interface 6224 can be connected to the host 6210 via a parallel Advanced Technology Attachment (PATH) bus, a serial Advanced Technology Attachment (SATA) bus, a Small Computer System Interface (SCSI), a Universal Serial Bus (USB), a High-Speed Peripheral Component Interconnect (PCIe), or a NAND interface. The memory controller 6220 can perform wireless communication functions using mobile communication protocols such as WiFi or LTE. The memory controller 6220 can connect to an external device (e.g., the host 6210 or another external device) and then transmit / receive data to / from the external device. For example, because the memory controller 6220 is configured to communicate with external devices according to one or more of various communication protocols, the memory system and data processing system according to the embodiments can be applied to wired / wireless electronic devices, especially mobile electronic devices.
[0170] Figure 12 This is a diagram illustrating another embodiment of a data processing system including a memory system. For example, Figure 12 An embodiment of a solid-state drive (SSD) 6300 that can be applied to a memory system is shown.
[0171] Reference Figure 12 The SSD 6300 may include a controller 6320 and a memory device 6340 including a plurality of non-volatile memory (NVMs). The controller 6320 may correspond to... Figure 1The controller 130 in the memory system 110, and the memory device 6340 can correspond to Figure 1 The memory device 150 in the memory system.
[0172] The controller 6320 can be connected to the memory device 6340 via multiple channels CH1 to CHi, and may include one or more processors 6321, error correction code (ECC) circuitry 6322, host interface 6324, buffer memory 6325, and memory interface, such as non-volatile memory interface 6326.
[0173] Buffer memory 6325 can temporarily store data provided from host 6310 or from multiple flash memories (NVMs) included in memory device 6340. Furthermore, buffer memory 6325 can temporarily store metadata of the multiple flash memories (NVMs), such as mapping data including a mapping table. Buffer memory 6325 can be implemented using any of a variety of volatile memories. Examples include dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate (DDR) SDRAM, low-power DDR (LPDDR) SDRAM, and graphics RAM (GRAM), or non-volatile memories such as ferroelectric RAM (FRAM), resistive RAM (RRAM or ReRAM), spin-transfer torque magnetic RAM (STT-MRAM), and phase-change RAM (PRAM). Figure 12 The buffer memory 6325 is shown to be implemented in the controller 6320. However, the buffer memory 6325 may be external to the controller 6320.
[0174] ECC circuit 6322 can calculate the error correction code (ECC) value of the data to be programmed into memory device 6340 during programming operations, perform error correction operations on the data read from memory device 6340 based on the ECC value during read operations, and perform error correction operations on the data recovered from memory device 6340 during failed data recovery operations.
[0175] The host interface 6324 can perform interface functions with an external device (e.g., host 6310), and the non-volatile memory interface 6326 can perform interface functions with a memory device 6340 connected via multiple channels.
[0176] In addition, it can provide applications. Figure 1The memory system 110 comprises multiple SSDs 6300s to implement a data processing system, such as a Redundant Array of Independent Disks (RAID) system. The RAID system may include multiple SSDs 6300s and a RAID controller for controlling the multiple SSDs 6300s. When the RAID controller performs a programming operation in response to a write command provided by the host 6310, the RAID controller can select one or more memory systems or SSDs 6300s based on multiple RAID levels (e.g., RAID level information from the write command provided by the host 6310 in the SSDs 6300s), and can output data corresponding to the write command to the selected SSD 6300. Furthermore, when the RAID controller performs a read operation in response to a read command provided by the host 6310, the RAID controller can select one or more memory systems or SSDs 6300s based on multiple RAID levels (e.g., RAID level information from the read command provided by the host 6310 in the SSDs 6300s), and can provide data read from the selected SSD 6300s to the host 6310.
[0177] Figure 13 This is a diagram illustrating another embodiment of a data processing system including a memory system. For example, Figure 13 An embodiment of an embedded multimedia card (eMMC) 6400 that can be applied to a memory system is shown.
[0178] Reference Figure 13 The eMMC 6400 may include a controller 6430 and a memory device 6440 implemented from one or more NAND flash memories. The controller 6430 may correspond to... Figure 1 The controller 130 in the memory system 110. The memory device 6440 can correspond to Figure 1 The memory device 150 in the memory system 110.
[0179] The controller 6430 can be connected to the memory device 6440 through multiple channels. The controller 6430 may include one or more cores 6432, a host interface 6431, and a memory interface such as a NAND interface 6433.
[0180] The kernel 6432 controls all operations of the eMMC 6400, the host interface 6431 performs the interface functions between the controller 6430 and the host 6410, and the NAND interface 6433 performs the interface functions between the memory device 6440 and the controller 6430. For example, the host interface 6431 can be used as a parallel interface, for example, see reference... Figure 1 The MMC interface is described. Additionally, the host interface 6431 can be used as a serial interface, such as an ultra-high-speed (UHS-I / UHS-II) interface.
[0181] Figures 14 to 17 These are illustrations showing other embodiments of a data processing system, including a memory system. For example, Figures 14 to 17 This illustrates a Universal Flash Memory (UFS) system that can be applied to memory systems.
[0182] Reference Figures 14 to 17 The UFS systems 6500, 6600, 6700, and 6800 may include host computers 6510, 6610, 6710, and 6810, UFS devices 6520, 6620, 6720, and 6820, and UFS cards 6530, 6630, 6730, and 6830, respectively. The host computers 6510, 6610, 6710, and 6810 can be used as application processors for wired / wireless electronic devices (e.g., mobile electronic devices), the UFS devices 6520, 6620, 6720, and 6820 can be used as embedded UFS devices, and the UFS cards 6530, 6630, 6730, and 6830 can be used as external embedded UFS devices or removable UFS cards.
[0183] The hosts 6510, 6610, 6710, and 6810, UFS devices 6520, 6620, 6720, and 6820, and UFS cards 6530, 6630, 6730, and 6830 in each UFS system 6500, 6600, 6700, and 6800 can communicate with external devices (e.g., wired / wireless electronic devices such as mobile electronic devices) via the UFS protocol, and the UFS devices 6520, 6620, 6720, and 6820 and the UFS cards 6530, 6630, 6730, and 6830 can be... Figure 1 The memory system 110 shown is used for implementation. For example, in UFS systems 6500, 6600, 6700, and 6800, UFS devices 6520, 6620, 6720, and 6820 can be implemented with reference to... Figures 11 to 13 The data processing system described is implemented in the form of a 6200, SSD 6300, or eMMC 6400, and UFS cards 6530, 6630, 6730, and 6830 can be referenced. Figure 10 The memory card system described is implemented in the form of 6100.
[0184] Furthermore, in UFS systems 6500, 6600, 6700, and 6800, hosts 6510, 6610, 6710, and 6810, UFS devices 6520, 6620, 6720, and 6820, and UFS cards 6530, 6630, 6730, and 6830 can communicate with each other via a UFS interface (e.g., MIPI M-PHY and MIPI Unified Protocol (UniPro) in the Mobile Industrial Processor Interface (MIPI)). Additionally, UFS devices 6520, 6620, 6720, and 6820, and UFS cards 6530, 6630, 6730, and 6830 can communicate with each other via any of the following protocols besides the UFS protocol: Universal Serial Bus (USB) Flash Drive (UFD), Multimedia Card (MMC), Secure Digital (SD), Mini SD, and Micro SD.
[0185] exist Figure 14 In the illustrated UFS system 6500, each of the host 6510, UFS device 6520, and UFS card 6530 may include a UniPro. The host 6510 can perform a switching operation to communicate with the UFS device 6520 and the UFS card 6530. For example, the host 6510 can communicate with the UFS device 6520 or the UFS card 6530 via a link-layer switching, such as an L3 switching at the UniPro. The UFS device 6520 and the UFS card 6530 can communicate with each other via a link-layer switching at the UniPro of the host 6510. In the illustrated embodiment, one UFS device 6520 and one UFS card 6530 are connected to the host 6510. However, multiple UFS devices and UFS cards can be connected in parallel or in a star configuration to the host 6510. A star configuration may include an arrangement where a single device is connected to multiple devices for centralized operation. Multiple UFS cards can be connected to the UFS device 6520 in parallel or in a star configuration, or in series or in a chain configuration.
[0186] exist Figure 15In the illustrated UFS system 6600, each of the host 6610, UFS device 6620, and UFS card 6630 can include a UniPro. The host 6610 can communicate with either the UFS device 6620 or the UFS card 6630 via a switching module 6640 that performs a switching operation, for example, a link-layer switching such as an L3 switch at the UniPro. The UFS device 6620 and the UFS card 6630 can communicate with each other via link-layer switching at the switching module 6640 at the UniPro. In the illustrated embodiment, one UFS device 6620 and one UFS card 6630 are connected to the switching module 6640. However, multiple UFS devices and UFS cards can be connected in parallel or in a star configuration to the switching module 6640. Multiple UFS cards can be connected in series or in a chain configuration to the UFS device 6620.
[0187] exist Figure 16 In the illustrated UFS system 6700, each of the host 6710, UFS device 6720, and UFS card 6730 can include a UniPro. The host 6710 can communicate with either the UFS device 6720 or the UFS card 6730 via a switching module 6740 that performs a handover operation, for example, by performing a link-layer handover, such as an L3 handover, at the UniPro. The UFS device 6720 and the UFS card 6730 can communicate with each other via link-layer handover by the switching module 6740 at the UniPro. The switching module 6740 can be integrated into a single module with the UFS device 6720, either internally or externally.
[0188] In the illustrated embodiment, a UFS device 6720 and a UFS card 6730 are connected to a switching module 6740. However, multiple modules may be connected to the host 6710 in parallel or in a star configuration, each module including the switching module 6740 and the UFS device 6720. In another example, multiple modules may be connected in series or in a chain to each other. Furthermore, multiple UFS cards may be connected to the UFS device 6720 in parallel or in a star configuration.
[0189] exist Figure 17In the illustrated UFS system 6800, each of the host 6810, UFS device 6820, and UFS card 6830 may include an M-PHY and a UniPro module. The UFS device 6820 can perform a switching operation to communicate with the host 6810 and the UFS card 6830. For example, the UFS device 6820 can communicate with either the host 6810 or the UFS card 6830 through a switching operation between the M-PHY and UniPro modules used for communication with the host 6810 and for communication with the UFS card 6830, for example, through a target identifier (ID) switching operation. The host 6810 and the UFS card 6830 can communicate with each other through target ID switching between the M-PHY and UniPro modules of the UFS device 6820.
[0190] In the illustrated embodiment, a UFS device 6820 is connected to a host 6810 and a UFS card 6830 is connected to the UFS device 6820. However, multiple UFS devices may be connected to the host 6810 in parallel or in a star topology, or in series or in a chain topology. Multiple UFS cards may be connected to the UFS device 6820 in parallel or in a star topology, or in series or in a chain topology.
[0191] Figure 18 This is a diagram illustrating another embodiment of a data processing system including a memory system. For example, Figure 18 This is a diagram illustrating a user system 6900 to which a memory system can be applied.
[0192] Reference Figure 18 The user system 6900 may include a user interface 6910, a memory module 6920, an application processor 6930, a network module 6940, and a storage module 6950. The application processor 6930 can drive components in the user system 6900, such as an operating system (OS), and includes controllers, interfaces, and a graphics engine for controlling the components included in the user system 6900. For example, the application processor 6930 may be configured as a system-on-a-chip (SoC).
[0193] Memory module 6920 can be used as main memory, working memory, buffer memory, or cache memory of user system 6900. Memory module 6920 may include volatile random access memory (DRAM). Examples include dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate (DDR) SDRAM, DDR2 SDRAM, DDR3 SDRAM, low-power DDR (LPDDR) SDRAM, LPDDR3 SDRAM, or LPDDR3 SDRAM. Memory module 6920 may also include non-volatile RAM such as phase-change RAM (PRAM), resistive RAM (ReRAM), magnetoresistive RAM (MRAM), or ferroelectric RAM (FRAM). For example, application processor 6930 and memory module 6920 may be packaged and mounted based on a stacked package (PoP).
[0194] Network module 6940 can communicate with external devices. For example, network module 6940 can support not only wired communication but also various wireless communication protocols. Examples include Code Division Multiple Access (CDMA), Global System for Mobile Communications (GSM), Wideband CDMA (WCDMA), CDMA-2000, Time Division Multiple Access (TDMA), Long Term Evolution (LTE), Global Microwave Access Interoperability (WiMAX), Wireless Local Area Network (WLAN), Ultra Wideband (UWB), Bluetooth, and Wireless Display (WI-DI), thereby enabling communication with wired / wireless electronic devices, especially mobile electronic devices. Therefore, according to embodiments, the memory system and data processing system can be applied to wired / wireless electronic devices. For example, network module 6940 can be included in application processor 6930.
[0195] Storage module 6950 can store data, such as data received from application processor 6930, and can then transfer the stored data to application processor 6930. Storage module 6950 can be implemented using a non-volatile semiconductor memory device. Examples include phase-change RAM (PRAM), magnetic RAM (MRAM), resistive RAM (ReRAM), NAND flash memory, NOR flash memory, and 3D NAND flash memory, and is provided as a removable storage medium such as a memory card or an external drive for user system 6900. Storage module 6950 can correspond to reference [reference missing]. Figure 1 The memory system 110 is described. Furthermore, the memory module 6950 can be implemented as described above. Figures 12 to 17 The SSD, eMMC, and UFS described.
[0196] According to one or more embodiments described herein, a memory device capable of dynamically adjusting the word line state check start time of the memory device, and a method of operating a memory system including the memory device, can be provided. Furthermore, according to one or more embodiments, a memory device capable of adjusting the word line state check start time of the memory device based on write buffer usage and maximum and minimum word line programming times, and a method of operating a memory system including the memory device, can be provided. Further, according to one or more embodiments, a memory device and a method of operating a memory system including the memory device can be provided to prevent quality of service (QoS) degradation even during garbage collection by maintaining a constant programming response time. Although this disclosure has been described with reference to specific embodiments, it will be apparent to those skilled in the art that various changes and modifications can be made without departing from the spirit and scope of this disclosure as defined by the appended claims. Therefore, the scope of this disclosure should not be limited to the above embodiments, but should be defined not only by the scope of the appended claims, but also by the equivalents of the claims. Embodiments can be combined to form other embodiments.
Claims
1. A memory system, comprising: A memory device, comprising at least one word line and at least one memory cell coupled to the word line; as well as A controller includes a write buffer that stores programming commands and data received from a host. The controller controls programming operations based on the programming commands to store the data in memory cells connected to the word line. During the execution of the programming operations, a status check time for the word line is set, and the status of the word line is checked according to a timeout signal generated based on the set status check time. The controller sets the status check time based on the sum of the basic status check time and the additional status check time. The basic status check time is determined based on the memory cell, and the additional status check time is determined based on the target programming response time, the maximum programming time of the word line, and the minimum programming time.
2. The memory system of claim 1, wherein, The controller includes: A status check time setting unit is used to set the status check time for the word line. The timeout generation unit generates the timeout signal based on the state check time set by the state check time setting unit; and The status check execution unit checks the status of the word line based on the timeout signal.
3. The memory system according to claim 2, wherein, The status check time setting unit checks whether the memory device is in a garbage collection state, and When the memory device is in the garbage collection state, the state check time setting unit checks whether the write buffer is saturated.
4. The memory system of claim 3, wherein, The status check time setting unit compares the target programming response time with the basic status check time when the write buffer is not in the saturated state.
5. The memory system of claim 4, wherein, When the target programming response time is greater than the basic state check time, the state check time setting unit compares the difference between the target programming response time and the basic state check time with the difference between the maximum word line programming time and the minimum word line programming time.
6. The memory system of claim 5, wherein, The status check time setting unit sets the status check time based on the basic status check time and the additional status check time.
7. The memory system of claim 6, wherein, When the difference between the target programming response time and the basic state check time is less than the difference between the maximum word line programming time and the minimum word line programming time, the additional state check time is calculated based on the difference between the maximum word line programming time and the minimum word line programming time.
8. The memory system of claim 6, wherein, When the difference between the target programming response time and the basic status check time is less than the difference between the maximum word line programming time and the minimum word line programming time, the additional status check time is calculated based on the difference between the maximum word line programming time and the minimum word line programming time and the ratio of the target usage of the write buffer to the actual usage of the write buffer.
9. The memory system of claim 6, wherein, When the difference between the target programming response time and the basic state check time is equal to or greater than the difference between the maximum word line programming time and the minimum word line programming time, the additional state check time is calculated based on the difference between the target programming response time and the basic state check time.
10. The memory system of claim 6, wherein, When the difference between the target programming response time and the basic status check time is equal to or greater than the difference between the maximum word line programming time and the minimum word line programming time, the additional status check time is calculated based on the difference between the target programming response time and the basic status check time, and the ratio of the target usage of the write buffer to the actual usage of the write buffer.
11. A method of operating a memory system, comprising: Perform a programming operation on at least one memory cell connected to at least one word line; Set the status check time for the word line during the execution of the programming operation; A timeout signal is generated based on the state check time; as well as The status of the word line is checked based on the timeout signal. The status check time is set based on the sum of the basic status check time and the additional status check time. The basic status check time is determined based on the memory cell, and the additional status check time is determined based on the target programming response time, the maximum programming time of the word line, and the minimum programming time.
12. The method of claim 11, further comprising: Check if the memory device is in garbage collection mode.
13. The method of claim 12, further comprising: When the memory device is in the garbage collection state, check whether the write buffer is saturated.
14. The method of claim 13, further comprising: When the write buffer is not in the saturated state, the target programming response time is compared with the basic state check time.
15. The method of claim 14, further comprising: When the target programming response time is greater than the basic state check time, the difference between the target programming response time and the basic state check time is compared with the difference between the maximum word line programming time and the minimum word line programming time.
16. The method of claim 15, further comprising: The state check time is set based on the basic state check time and the additional state check time.
17. The method of claim 16, wherein, When the difference between the target programming response time and the basic state check time is less than the difference between the maximum word line programming time and the minimum word line programming time, the additional state check time is calculated based on the difference between the maximum word line programming time and the minimum word line programming time.
18. The method of claim 16, wherein, When the difference between the target programming response time and the basic status check time is less than the difference between the maximum word line programming time and the minimum word line programming time, the additional status check time is calculated based on the difference between the maximum word line programming time and the minimum word line programming time and the ratio of the target usage of the write buffer to the actual usage of the write buffer.
19. The method of claim 16, wherein, When the difference between the target programming response time and the basic state check time is equal to or greater than the difference between the maximum word line programming time and the minimum word line programming time, the additional state check time is calculated based on the difference between the target programming response time and the basic state check time.
20. The method of claim 16, wherein, When the difference between the target programming response time and the basic status check time is equal to or greater than the difference between the maximum word line programming time and the minimum word line programming time, the additional status check time is calculated based on the difference between the target programming response time and the basic status check time, and the ratio of the target usage of the write buffer to the actual usage of the write buffer.
21. A memory system comprising: A memory device, comprising at least one memory cell connected to at least one word line; as well as Controller: Perform programming operations on the memory cells; Determine the status check time for the word line; A timeout signal is generated based on the state check time; and In response to the timeout signal, a status check command is transmitted to the memory device, causing the memory device to check the busy or ready state of the word line associated with the programming operation on the memory cell, and to notify the controller of the status of the word line. The state check time is determined based on the sum of the basic state check time and the additional state check time. The basic state check time is determined based on the memory cell, and The additional state check time is determined based on the target programming response time, the maximum programming time of the word line, and the minimum programming time.
Citation Information
Patent Citations
SELF-HEATING HOLLOW NANOREACTOR CATALYST FOR BIOORTHOGONAL ORGANIC REACTION, MANUFACTURING METHOD FOR THE SAME aND MANUFACTURING METHOD FOR COUMARIN USING THE SAME
KR1020210130562A
Semiconductor system performing status read for semiconductor device and operating method thereof
US20160239206A1
