Multi-namespace storage device and operating method thereof, multi-namespace electronic system

By using different mapping attributes based on the host's namespace classification, logical block numbers and logical page numbers are mapped to different memory blocks and memory pages respectively, solving the performance degradation problem of multi-namespace NVMe storage devices in the prior art, and achieving more efficient physical address utilization and performance improvement.

CN114490427BActive Publication Date: 2026-11-10SAMSUNG ELECTRONICS CO LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202111141111.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2020-10-23
Filing Date
2021-09-28
Publication Date
2026-11-10
Estimated Expiration
2041-09-28

AI Technical Summary

Technical Problem

In existing technologies, NVMe storage devices with multiple namespaces suffer from performance degradation due to the division at the logical address level, and cannot effectively utilize the unique characteristics of physical addresses to meet the needs of different namespaces.

Method used

By using different mapping attributes based on the host's namespace classification, logical block numbers and logical page numbers are mapped to different memory blocks and memory pages respectively, thus achieving dedicated mapping of physical addresses and meeting the performance requirements of different namespaces.

Benefits of technology

It improves the performance of storage devices, especially for namespaces used for sequential and random writes, thereby enhancing the overall efficiency and reliability of the storage devices.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114490427B_ABST
    Figure CN114490427B_ABST
Patent Text Reader

Abstract

Provided are a multi-namespace storage device and an operating method thereof, and a multi-namespace electronic system. The multi-namespace storage device includes a nonvolatile memory including a first memory block and a second memory block different from the first memory block, and a memory controller that receives a command for requesting creation of a first namespace and a second namespace from a host, and receives a physical mapping command for commanding a physical mapping of the first namespace, the first namespace including a first logical block number, and the second namespace including a second logical page number not included in the first logical block number. The memory controller performs a first mapping operation by mapping the first logical block number to the first memory block and a second mapping operation by mapping the second logical page number to a second memory page included in the second memory block in response to the physical mapping command.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] This application claims priority to Korean Patent Application No. 10-2020-0137977, filed on October 23, 2020, with the Korean Intellectual Property Office, the entire disclosure of which is incorporated herein by reference. Technical Field

[0002] Embodiments of this disclosure relate to a multi-namespace storage device, an electronic system including the storage device, and a method of operating the storage device. Background Technology

[0003] Currently, research is underway on the implementation of non-volatile memory fast (NVMe) storage devices for service level agreements (SLAs) or weighted round-robin (WRR) scheduling in multi-tenant environments. To this end, research is also being conducted to improve architectures such as physical functionality, virtual functionality, and multiple command spaces.

[0004] With multi-namespace, a single NVMe storage device can be partitioned into regions defined as namespaces or logical addresses, and each region can be used for different purposes.

[0005] For example, zones can be divided according to their purpose, such as zones primarily used for journaling (using metadata or random writes) and zones primarily used for sequential writes (such as sequential mode or backups). However, this zone division only applies to logical addresses, while physical addresses are actually shared regardless of their purpose, which can lead to performance degradation. Summary of the Invention

[0006] This disclosure provides a multi-namespace storage device with different mapping attributes based on the namespace classification of the host.

[0007] This disclosure also provides a multi-namespace electronic system with different mapping attributes based on the namespace classification of the host.

[0008] This disclosure also provides a method for operating a multi-namespace storage device that has different mapping attributes depending on the namespace classification of the host.

[0009] This disclosure also provides a multi-namespace storage device that maps dedicated physical addresses to namespaces that utilize sequential writes.

[0010] According to one aspect of this disclosure, a multi-namespace storage device includes: non-volatile memory including a first memory block and a second memory block different from the first memory block; and a memory controller that receives from a host a command to request the creation of a first namespace and a second namespace, and receives a physical mapping command to command a physical mapping of the first namespace, the first namespace including a first logical block number, and the second namespace including a second logical page number not included in the first logical block number. In response to the physical mapping command, the memory controller performs a first mapping operation by mapping the first logical block number to the first memory block, and performs a second mapping operation by mapping the second logical page number to a second memory page included in the second memory block.

[0011] According to one aspect of this disclosure, a multi-namespace electronic system includes: a plurality of non-volatile memories, including a first non-volatile memory and a second non-volatile memory; a memory controller that controls the plurality of non-volatile memories; and a host connected to the memory controller that sends commands to request the creation of a first namespace and a second namespace, the first namespace including a first logical block number, and the second namespace including a second logical page number not included in the first logical block number. The host sends a physical mapping command to instruct the physical mapping of the first namespace, and the memory controller, in response to the physical mapping command, performs a first mapping operation by mapping the first logical block number to a first memory block in the first non-volatile memory, and performs a second mapping operation by mapping the second logical page number to a second memory page included in the second non-volatile memory.

[0012] According to one aspect of this disclosure, a method of operating a multi-namespace storage device includes: sending a command for requesting the creation of a first namespace to a memory controller, the first namespace including a first logical block number; sending a first write command for the first logical block number together with a physical mapping command for commanding a physical mapping of the first namespace to the memory controller; in response to the physical mapping command, storing first mapping information from the first logical block number to a first memory block corresponding to the first logical block number in a mapping table; in response to the physical mapping command, performing a first write operation on the first memory block; after sending the first write command, sending a second write command for the first logical block number to the memory controller; and performing a second write operation on the first memory block based on the second write command and the mapping table. Attached Figure Description

[0013] The above and other features of this disclosure will become clearer from the detailed description of embodiments thereof with reference to the accompanying drawings, in which:

[0014] Figure 1This is a block diagram of an electronic system according to an embodiment of the present disclosure;

[0015] Figure 2 This is a block diagram of an electronic system including a storage device according to embodiments of the present disclosure;

[0016] Figure 3 yes Figure 2 A block diagram of the memory controller;

[0017] Figure 4 yes Figure 2 A block diagram of non-volatile memory;

[0018] Figure 5 This is an exemplary perspective view of a non-volatile memory according to embodiments of the present disclosure;

[0019] Figure 6 This is an exemplary circuit diagram of a memory cell array according to an embodiment of the present disclosure;

[0020] Figure 7 The interior of a non-volatile memory according to an embodiment of the present disclosure is schematically shown;

[0021] Figure 8 and Figure 9 This is a diagram illustrating a method of operating a storage device according to an embodiment of the present disclosure;

[0022] Figure 10 A logical address region used in an electronic system according to an embodiment of the present disclosure is shown;

[0023] Figure 11 It is used to explain the basis Figure 10 A diagram illustrating a hybrid mapping in an electronic system where physical and logical mappings are used together;

[0024] Figure 12 It shows the relationship with Figure 11 The mapping table corresponding to the mapping;

[0025] Figure 13 A logical address region used in an electronic system according to an embodiment of the present disclosure is shown;

[0026] Figure 14 It shows that according to Figure 13 Hybrid mapping used in electronic systems in embodiments;

[0027] Figures 15 to 17 It is a graph used to explain the effects of the electronic system according to the embodiments of this disclosure;

[0028] Figure 18 This is a block diagram of an electronic system including a storage device according to embodiments of the present disclosure;

[0029] Figure 19 The internal structure of a non-volatile memory according to an embodiment of the present disclosure is schematically shown; and

[0030] Figure 20 This is an exemplary circuit diagram of a portion of a memory cell array according to an embodiment of the present disclosure. Detailed Implementation

[0031] In the following description, embodiments of the present disclosure will be described more fully with reference to the accompanying drawings. Throughout the drawings, the same reference numerals may denote the same elements. For ease of explanation, repeated descriptions of components and technical aspects previously described in the specification may be omitted thereafter.

[0032] It will be understood that the terms “first,” “second,” “third,” etc., are used herein to distinguish one element from another, and the elements are not limited by these terms. Thus, a “first” element in one embodiment may be described as a “second” element in another embodiment.

[0033] As used herein, unless the context clearly indicates otherwise, the singular forms “a,” “one,” and “the” are also intended to include the plural forms.

[0034] Figure 1 This is a block diagram of a system (e.g., an electronic system) 1000 according to an embodiment of the present disclosure. Figure 1 System 1000 can be a mobile system (such as a portable communication terminal (mobile phone), smartphone, tablet computer, wearable device, healthcare device, or Internet of Things (IoT) device). However, Figure 1 The system 1000 is not limited to such a mobile system, and can also be, for example, a personal computer, a laptop computer, a server, a media player, or an automotive device (such as a navigation device).

[0035] Reference Figure 1 The system 1000 may include a main processor 1100, memories 1020a and 1020b and storage devices 1010a and 1010b, and may additionally include one or more of an image capturing device 1410, a user input device 1420, a sensor 1430, a communication device 1440, a display 1450, a speaker 1460, a power supply device 1470 and a connection interface 1480.

[0036] The main processor 1100 can control the overall operation of the system 1000. For example, the main processor 1100 can control the operation of other components constituting the system 1000. The main processor 1100 can be implemented as, for example, a general-purpose processor, a special-purpose processor, or an application processor.

[0037] The main processor 1100 may include one or more central processing unit (CPU) cores 1110, and may also include a controller 1120 for controlling memories 1020a and 1020b and / or storage devices 1010a and 1010b. According to one embodiment, the main processor 1100 may also include an accelerator block 1130, which is dedicated circuitry for high-speed data operations, such as artificial intelligence (AI) data operations. The accelerator block 1130 may include, for example, a graphics processing unit (GPU), a neural processing unit (NPU), and / or a data processing unit (DPU), and may be implemented as a separate chip physically independent of other components of the main processor 1100.

[0038] Memory 1020a and 1020b can be used as the main memory device of system 1000, and may include volatile memory (such as static random access memory (SRAM) and / or dynamic random access memory (DRAM) as examples), and may also include non-volatile memory (such as flash memory, phase-change random access memory (PRAM) and / or resistive random access memory (RRAM) as examples). Memory 1020a and 1020b may also be implemented in the same package as the main processor 1100. Although Figure 1 Two memories 1020a and 1020b and two storage devices 1010a and 1010b are shown, but the embodiments are not limited thereto. For example, in some embodiments, system 1000 may include one memory or three or more memories, and system 1000 may include one storage device or three or more storage devices.

[0039] Storage devices 1010a and 1010b can be used as non-volatile storage devices that store data regardless of whether power is supplied, and can have a relatively large storage capacity than memory devices 1020a and 1020b. Storage devices 1010a and 1010b may each include storage controllers 1200a and 1200b and non-volatile memory (NVM) 1300a and 1300b, which store data under the control of storage controllers 1200a and 1200b. Non-volatile memory 1300a and 1300b may include V-NAND flash memory with a two-dimensional (2D) or three-dimensional (3D) structure, and may also include other types of non-volatile memory (such as PRAM and / or RRAM).

[0040] Storage devices 1010a and 1010b included in system 1000 may be physically separate from the main processor 1100, or may be implemented in the same package as the main processor 1100. Furthermore, storage devices 1010a and 1010b may be in the form of memory cards and can therefore be detachably coupled to other components of system 1000 via an interface (such as connection interface 1480, described later). Storage devices 1010a and 1010b may be, but are not necessarily limited to, devices employing standard protocols (such as Universal Flash Memory (UFS)).

[0041] The image capturing device 1410 can capture still images or moving images, and can be, for example, a camera, a video camera, and / or a webcam.

[0042] User input device 1420 can receive various types of data from the user of system 1000, and can be, for example, a touchpad, keypad, keyboard, mouse and / or microphone.

[0043] Sensor 1430 can detect various types of physical inputs that can be obtained from outside the system 1000, and can convert the detected physical inputs into electrical signals. Sensor 1430 can be, for example, a temperature sensor, a pressure sensor, a brightness sensor, a position sensor, an acceleration sensor, a biosensor, and / or a gyroscope.

[0044] The communication device 1440 can transmit signals to other devices outside the system 1000 or receive signals from other devices outside the system 1000, according to various communication protocols. The communication device 1440 may include, for example, an antenna, a transceiver, and / or a modem.

[0045] The display 1450 can be used as an output device to output visual information to the user of the system 1000, and the speaker 1460 can be used as an output device to output audio information to the user of the system 1000.

[0046] The power supply unit 1470 can convert power supplied from a battery built into the system 1000 and / or an external power source, and supply power to each component of the system 1000.

[0047] The connection interface 1480 provides a connection between the system 1000 and external devices, which connect to the system 1000 to exchange data. The connection interface 1480 can be implemented as various interfaces, such as, for example, an Advanced Technology Attachment (ATA) interface, a Serial ATA (SATA) interface, an external SATA (e-SATA) interface, a Small Computer System Interface (SCSI) interface, a Serial Attached SCSI (SAS) interface, a Peripheral Component Interconnect (PCI) interface, a PCIe (PCIe) interface, an NVM Fast (NVMe) interface, an IEEE 1394 interface, a Universal Serial Bus (USB) interface, a Secure Digital Card (SD) interface, a Multimedia Card (MMC) interface, an Embedded Multimedia Card (eMMC) interface, a Universal Flash Memory (UFS) interface, an Embedded Universal Flash Memory (eUFS) interface, and a Compact Flash Memory (CF) card interface.

[0048] Figure 2 This is a block diagram of an electronic system 1 including a storage device 10 according to an embodiment of the present disclosure.

[0049] Reference Figure 2 The electronic system 1 may include a storage device 10 and a host device (or host) 100. The host device 100 can control the operation of the storage device 10. The storage device 10 can be connected to... Figure 1 The storage devices 1010a and 1010b correspond to this.

[0050] In some embodiments, storage device 10 may be a flash memory device including one or more flash memory chips. In one embodiment, storage device 10 may be an embedded memory of electronic system 1. For example, storage device 10 may be an eMMC or embedded UFS memory device.

[0051] According to one embodiment, the storage device 10 may be an external memory removable from the electronic system 1. For example, the storage device 10 may be a UFS memory card, a compact flash (CF) card, a secure digital card (SD) card, a micro-SD card, a mini-SD card, an extreme digital (xD) card, or a memory stick.

[0052] The host device 100 may include a processor 110, a host memory 120, and a host controller 130. The processor 110, host memory 120, and host controller 130 can send signals to and receive signals from each other via an internal bus.

[0053] The processor (CPU core) 110 can execute various software loaded into the host memory 120. For example, the processor 110 can execute operating systems and applications. The processor 110 can be configured as a homogeneous multi-core processor or a heterogeneous multi-core processor.

[0054] Host memory 120 can be used as main memory or cache memory. Furthermore, host memory 120 can be used as driver memory for driver software or firmware. Applications or data to be processed by processor 110 can be loaded into host memory 120. For example, file system 121, applications, and device drivers can be loaded into host memory 120.

[0055] The file system 121 organizes files or data when they are stored in the storage device 10. The file system 121 can provide the logical address ADDR_L to the storage device 10 according to commands (e.g., a write command WCMD or a read command). The file system 121 can be used depending on the specific operating system running on the host device 100.

[0056] The host device 100 can manage the storage space of the storage device 10, write user data to the storage device 10, and read user data from the storage device 10 using the file system 121. The file system 121 can be implemented by software or firmware.

[0057] The host controller 130 can convert the format of data (such as commands (e.g., write command WCMD or physical mapping command PMCMD), logical address ADDR_L, and data DATA) corresponding to various access requests issued by the host device 100, or convert the format of exchanged commands, and send the data or exchanged commands to the storage device 10. The protocol of the host controller 130 can be compatible with... Figure 1 The connection interface corresponds to 1480.

[0058] In some embodiments, the host device 100 may provide a physical mapping command PMCMD, distinct from the write command WCMD, to the storage device 10. In one embodiment, the physical mapping command PMCMD may be included in a portion of the write command WCMD.

[0059] Storage device 10 may include memory controller 200, buffer memory 202, and non-volatile memory 300. Storage device 10 may access non-volatile memory 300 or perform requested operations in response to commands received from host device 100.

[0060] The memory controller 200 can control the operation of the non-volatile memory 300 through channel CH. The memory controller 200 can receive write command WCMD and logical address ADDR_L from the host device 100, and write data DATA into the non-volatile memory 300.

[0061] The memory controller 200 can determine the mapping attributes of the logical address ADDR_L received from the host device 100 in response to the physical mapping command PMCMD.

[0062] Please refer to later Figure 3 The configuration and operation of the memory controller 200 are described in detail.

[0063] The buffer memory 202 can temporarily store write data or read data. Write data temporarily stored in the buffer memory 202 can be written to the non-volatile memory 300, and read data temporarily stored in the buffer memory 202 can be sent to the host device 100 through the memory controller 200.

[0064] The non-volatile memory 300 can perform read / write operations under the control of the memory controller 200. The non-volatile memory 300 may include multiple memory blocks BLK 0 to BLK N-1, each of which may include multiple pages. Each page may include multiple memory cells. In one embodiment, the non-volatile memory 300 can perform erase operations block-by-block and write or read operations page-by-page.

[0065] A physical address can correspond to a specific region of the non-volatile memory 300. For example, the physical address used to select a page can be the physical page number (PPN), and the physical address used to select a memory block can be the physical block number (PBN).

[0066] In some embodiments, the non-volatile memory 300 may include a plurality of memory cells. For example, the memory cells may be NAND flash memory cells. However, this disclosure is not limited thereto, and the memory cells may also be, for example, resistive memory cells (such as RRAM, PRAM, or magnetic RAM (MRAM)).

[0067] Figure 3 yes Figure 2 Block diagram of memory controller 200. Figure 4 yes Figure 2 Block diagram of non-volatile memory 300.

[0068] Reference Figure 3 and Figure 4 The memory controller 200 may include a processor 210, a memory 211, a host interface (I / F) 212, a memory interface (I / F) 213, and a working memory 220.

[0069] Processor 210 may include, for example, a CPU, a controller, or an application-specific integrated circuit (ASIC). Processor 210 can control the overall operation of memory controller 200. Processor 210 can control memory controller 200 by driving firmware loaded into working memory 220.

[0070] Memory 211 can store information for storage device 10 (see...) Figure 2 The initial booting code data.

[0071] The memory controller 200 and the host device 100 can be connected via the host interface 212. That is, data DATA can be sent and received via the host interface 212. The host interface 212 may include, for example, ATA, SATA, e-SATA, USB, or NVMe.

[0072] The memory controller 200 and the non-volatile memory 300 can be connected via the memory interface 213. That is, data DATA, control signals CTRL, addresses ADDR, commands CMD, etc., can be sent and received via the memory interface 213. The working memory 220 can be implemented as, for example, a cache memory, DRAM, SRAM, or flash memory.

[0073] Working memory 220 may include a flash translation layer (FTL). The FTL may include system software that manages write, read, and erase operations of the non-volatile memory 300. For example, the FTL may include firmware. The FTL may be loaded into working memory 220. The firmware of the FTL may be executed by processor 210.

[0074] The working memory 220 may include a namespace manager module 221, a wear leveling manager module 222, a garbage collection manager module 223, a mapping table manager module 224, and an address mapping table (or mapping table) 225.

[0075] Working memory 220 can translate logical addresses ADDR_L into physical addresses using address mapping table 225 and provide the physical addresses to non-volatile memory 300. Working memory 220 can manage the memory cells of non-volatile memory 300. For example, working memory 220 can perform garbage collection and wear leveling operations on blocks of the memory cell array (e.g., also referred to as memory array) 310 of non-volatile memory 300.

[0076] The namespace manager module 221 can dynamically create namespaces in response to requests from users of the host device 100 (i.e., namespace creation request commands). Here, the namespace manager module 221 can create namespaces by allocating logical address regions of the newly created namespace sequentially from the logical address regions of previously created namespaces. The namespace manager module 221 can update the address mapping table 225 by requesting the mapping table manager module 224 during namespace creation and deletion operations.

[0077] The loss leveling manager module 222 can manage the loss level of the non-volatile memory 300 by adjusting the program / erase (P / E) cycle.

[0078] The memory controller 200 can control the garbage collection of the non-volatile memory 300 using the garbage collection manager module 223. For example, the garbage collection manager module 223 can control the garbage collection of the non-volatile memory 300 using metadata, etc.

[0079] Here, garbage collection is performed to search for or secure free blocks in the non-volatile memory 300. Because data is written page by page but erased block by block, adjustment methods can be utilized. Therefore, through garbage collection, free blocks can be secured by writing valid pages to another block and erasing the block containing the valid pages. The performance of the storage device 10 can be improved through the control of garbage collection.

[0080] The address mapping table 225 can be updated by reflecting the results of operations such as namespace creation / deletion, wear leveling, and garbage collection.

[0081] According to an embodiment, the mapping table manager module 224 can receive physical mapping commands PMCMD (see ...) from the host device 100. Figure 2 In response to the physical mapping command PMCMD, the mapping table manager module 224 exclusively maps a specific logical address to a specific physical address. That is, unless the physical mapping is modified, the mapping table manager module 224 can prevent a physically mapped physical address from being mapped to another logical address.

[0082] According to some embodiments, the mapping table manager module 224 can map other physically unmapped logical addresses to physically unmapped physical addresses that can be effectively mapped, based on the results of garbage collection operations and wear leveling operations.

[0083] Reference Figure 4The non-volatile memory 300 may include a memory cell array 310, an address decoder 320, a voltage generator 330, a read / write circuit 340, and control logic 350.

[0084] The memory cell array 310 can be connected to the address decoder 320 via word lines WL. The memory cell array 310 can be connected to the read / write circuitry 340 via bit lines BL. The memory cell array 310 may include multiple memory cells. For example, memory cells arranged in the row direction can be connected to word lines WL. For example, memory cells arranged in the column direction can be connected to bit lines BL.

[0085] Address decoder 320 can be connected to memory cell array 310 via word line WL. Address decoder 320 can operate in response to control logic 350. Address decoder 320 can receive address ADDR from memory controller 200. Address decoder 320 can receive voltages for programming and reading operations from voltage generator 330.

[0086] Address decoder 320 can decode the row address in the received address ADDR. Address decoder 320 can use the decoded row address to select the word line WL. The decoded column address DCA can be provided to the read / write circuit 340. For example, address decoder 320 may include a row decoder, a column decoder, and an address buffer.

[0087] Voltage generator 330 can generate voltages for access operations under the control of control logic 350. For example, voltage generator 330 can generate programming voltages and programming verification voltages for performing programming operations. Similarly, voltage generator 330 can generate read voltages for performing read operations, and erase voltages and erase verification voltages for performing erase operations. Furthermore, voltage generator 330 can provide the voltages for each operation to address decoder 320.

[0088] The read / write circuit 340 can be connected to the memory cell array 310 via bit line BL. The read / write circuit 340 can exchange data DATA with the memory controller 200. The read / write circuit 340 can operate in response to control logic 350. The read / write circuit 340 can receive the decoded column address DCA from the address decoder 320. The read / write circuit 340 can use the decoded column address DCA to select bit line BL.

[0089] For example, read / write circuitry 340 can program received data DATA into memory cell array 310. Read / write circuitry 340 can read data from memory cell array 310 and provide the read data to an external device (e.g., memory controller 200). For example, read / write circuitry 340 may include a sense amplifier, a write driver, column select circuitry, and a page buffer.

[0090] Control logic 350 can be connected to address decoder 320, voltage generator 330, and read / write circuitry 340. Control logic 350 can control the operation of non-volatile memory 300. Control logic 350 can operate in response to control signals CTRL and commands CMD (e.g., write and read commands) received from memory controller 200. Control logic 350 can perform garbage collection on memory cell array 310 under the control of memory controller 200.

[0091] Figure 5 This is an exemplary perspective view of a non-volatile memory 300 according to an embodiment of the present disclosure.

[0092] Reference Figure 4 and Figure 5 According to some embodiments, the non-volatile memory 300 may include a plurality of semiconductor layers LA1 to LAn. Each of the semiconductor layers LA1 to LAn may be a memory chip (e.g., a DRAM memory chip). Optionally, some of the semiconductor layers LA1 to LAn may be for interaction with external devices (e.g., Figure 1 The host device 100) communicates with the main chip via an interface, and the other semiconductor layers in semiconductor layers LA1 to LAn can be slave chips that store data.

[0093] For example, the nth semiconductor layer LAn and the first semiconductor layer LA1 of the non-volatile memory 300 may both be semiconductor chips including a memory cell array 310. Semiconductor layers LA1 to LAn can send signals to and receive signals from each other via through-silicon vias (or "through-silicon vias") (TSVs). The configuration and arrangement of the non-volatile memory 300 according to embodiments of this disclosure are not limited to the examples above.

[0094] Figure 6 This is an exemplary circuit diagram of a memory cell array 310 according to an embodiment of the present disclosure.

[0095] Reference Figure 6Multiple unit strings NS11, NS21, NS31, NS12, NS22, NS32, NS13, NS23, and NS33 can be disposed on the substrate in a first direction X and a second direction Y. Unit strings NS11, NS21, NS31, NS12, NS22, NS32, NS13, NS23, and NS33 can extend in a third direction Z. Unit strings NS11, NS21, NS31, NS12, NS22, NS32, NS13, NS23, and NS33 can be commonly connected to a common source line CSL formed on or within the substrate. Although in Figure 6 In this embodiment, the common source line CSL is connected to the lowest point of the cell strings NS11, NS21, NS31, NS12, NS22, NS32, NS13, NS23, and NS33 in the third direction Z, but embodiments of this disclosure are not limited thereto. For example, in some embodiments, the common source line CSL may be electrically connected to the lowest point of the cell strings NS11, NS21, NS31, NS12, NS22, NS32, NS13, NS23, and NS33 in the third direction Z, and the common source line CSL is not physically located at the bottom of the cell strings NS11, NS21, NS31, NS12, NS22, NS32, NS13, NS23, and NS33. Furthermore, although in Figure 6 In this array, cell strings NS11, NS21, NS31, NS12, NS22, NS32, NS13, NS23 and NS33 are arranged in a 3×3 array, but the arrangement and number of cell strings in the non-volatile memory cell array 310 are not limited thereto.

[0096] Some unit strings NS11, NS12, and NS13 can be connected to the first ground select line GSL1. Some unit strings NS21, NS22, and NS23 can be connected to the second ground select line GSL2. Some unit strings NS31, NS32, and NS33 can be connected to the third ground select line GSL3.

[0097] In addition, some unit strings NS11, NS12, and NS13 can be connected to the first select line SSL1. Some unit strings NS21, NS22, and NS23 can be connected to the second select line SSL2. Some unit strings NS31, NS32, and NS33 can be connected to the third select line SSL3.

[0098] Each of the cell strings NS11, NS21, NS31, NS12, NS22, NS32, NS13, NS23, and NS33 may include a string select transistor (SST) connected to the string select line. Furthermore, each of the cell strings NS11, NS21, NS31, NS12, NS22, NS32, NS13, NS23, and NS33 may include a ground select transistor (GST) connected to the ground select line.

[0099] The ground select transistor of each of the cell strings NS11, NS21, NS31, NS12, NS22, NS32, NS13, NS23, and NS33 may be connected to the common source line CSL. Furthermore, each of the cell strings NS11, NS21, NS31, NS12, NS22, NS32, NS13, NS23, and NS33 may include a plurality of memory cells sequentially stacked in a third direction Z between the ground select transistor and the string select transistor. In some embodiments, each of the cell strings NS11, NS21, NS31, NS12, NS22, NS32, NS13, NS23, and NS33 may include a dummy cell between the ground select transistor and the string select transistor. Furthermore, the number of string select transistors included in each string is not limited to... Figure 6 The quantities shown in the figure.

[0100] For example, cell string NS11 may include a ground selection transistor GST11 located at the bottom in the third direction Z, a plurality of memory cells M11_1 to M11_8 sequentially stacked on the ground selection transistor GST11 in the third direction Z, and a string selection transistor SST11 stacked on the topmost memory cell M11_8 in the third direction Z. Similarly, cell string NS21 may include a ground selection transistor GST21 located at the bottom in the third direction Z, a plurality of memory cells M21_1 to M21_8 sequentially stacked on the ground selection transistor GST21 in the third direction Z, and a string selection transistor SST21 stacked on the topmost memory cell M21_8 in the third direction Z. Furthermore, cell string NS31 may include a ground selection transistor GST31 located at the bottom in the third direction z, a plurality of memory cells M31_1 to M31_8 sequentially stacked on the ground selection transistor GST31 in the third direction Z, and a string selection transistor SST31 stacked on the topmost memory cell M31_8 in the third direction Z. Other strings can also be configured in a similar way.

[0101] Memory cells located at the same height from the substrate or ground selection transistor on the third direction Z can be electrically connected via word lines. For example, memory cells at the height where memory cells M11_1, M21_1, and M31_1 are formed can be connected to the first word line WL1. Furthermore, memory cells at the height where memory cells M11_2, M21_2, and M31_2 are formed can be connected to the second word line WL2. The arrangement and structure of memory cells connected to the third word lines WL3 through the eighth word lines WL8 are similar to the above example and will not be described further.

[0102] The ends of the string select transistors in each of the unit strings NS11, NS21, NS31, NS12, NS22, NS32, NS13, NS23, and NS33 can be connected to bit lines BL1, BL2, or BL3. For example, string select transistors SST11, SST21, and SST31 can be connected to bit line BL1, which extends in the second direction Y. The description of other string select transistors connected to bit lines BL2 and BL3 is similar to that described above and will therefore be omitted.

[0103] A page can be formed by a memory cell corresponding to a string select line (or ground select line) and a word line. Write and read operations can be performed page by page. Each memory cell in each page can store two or more bits. Bits written to memory cells in each page can form logical pages.

[0104] The memory cell array 310 can be configured as a 3D memory array. In a 3D memory array, an array of memory cells having active regions disposed on a substrate, along with circuitry associated with the operation of the memory cells, is monolithically formed at one or more physical levels. The circuitry associated with the operation of the memory cells can be located in or on the substrate. The term "monolithically formed" means that the layer at each level of the 3D array is directly deposited on the layer at the lower level of the 3D array. Optionally, the circuitry associated with the operation of the memory cells can be connected to a contact at the top in the third direction Z. This will refer to... Figure 7 Describe it in detail.

[0105] Figure 7 The interior of a non-volatile memory 300 according to an embodiment of the present disclosure is schematically shown.

[0106] Reference Figure 7 The non-volatile memory 300 according to embodiments of the present disclosure may have a chip-to-chip (C2C) structure. Figure 7 In the non-volatile memory 300, the cell region CELL can be connected with... Figure 5 The memory cell array 310 corresponds to this.

[0107] A C2C structure can be formed by fabricating an upper chip including cell regions (CELL) on a first wafer, fabricating a lower chip including peripheral circuit regions (PERI) on a second wafer different from the first wafer, and then connecting the upper and lower chips using a bonding method. For example, the bonding method can refer to a method of electrically connecting bonding metal formed on the topmost metal layer of the upper chip to bonding metal formed on the topmost metal layer of the lower chip. For example, when the bonding metal is made of copper (Cu), the bonding method can be a Cu-Cu bonding method. The bonding metal can also be made of aluminum or tungsten.

[0108] Each of the peripheral circuit region PERI and cell region CELL of the non-volatile memory 300 according to embodiments of the present disclosure may include an external pad (or “solder pad”) bonding region PA, a word line bonding region WLBA, and a bit line bonding region BLBA.

[0109] The peripheral circuit region (PERI) may include a first substrate 1210, an interlayer insulating layer 1215, a plurality of circuit elements 1220a to 1220c formed on the first substrate 1210, first metal layers 1230a to 1230c respectively connected to the circuit elements 1220a to 1220c, and second metal layers 1240a to 1240c formed on the first metal layers 1230a to 1230c. In one embodiment, the first metal layers 1230a to 1230c may be made of tungsten, which has relatively high resistance, and the second metal layers 1240a to 1240c may be made of copper, which has relatively low resistance.

[0110] Although only the first metal layers 1230a to 1230c and the second metal layers 1240a to 1240c are shown and described herein, embodiments of this disclosure are not limited thereto. For example, in some embodiments, one or more metal layers may further be formed on the second metal layers 1240a to 1240c. At least some of the metal layers formed on the second metal layers 1240a to 1240c may be made of aluminum having a lower resistance than the copper forming the second metal layers 1240a to 1240c.

[0111] Interlayer insulating layer 1215 may be disposed on first substrate 1210 to cover circuit elements 1220a to 1220c, first metal layers 1230a to 1230c and second metal layers 1240a to 1240c, and may include insulating material (such as silicon oxide or silicon nitride).

[0112] Lower bonding metals 1271b and 1272b can be formed on the second metal layer 1240b of the word line bonding region WLBA. In the word line bonding region WLBA, the lower bonding metals 1271b and 1272b of the peripheral circuit region PERI can be electrically connected to the upper bonding metals 1371b and 1372b of the cell region CELL by a bonding method. The lower bonding metals 1271b and 1272b and the upper bonding metals 1371b and 1372b can be made of, for example, aluminum, copper or tungsten.

[0113] A cell region (CELL) can provide at least one memory block. The cell region (CELL) may include a second substrate 1310 and a common-source pole line 1320 (corresponding to...). Figure 5 (CSL). Multiple word lines 1331 to 1338 (1330, corresponding to...) Figure 5 WL1 to WL8 can be stacked on the second substrate 1310 along a third direction Z perpendicular to the upper surface of the second substrate 1310. Serial select line and ground select line can be respectively positioned above and below word line 1330, and word line 1330 can be positioned between serial select line and ground select line.

[0114] In the bit line bonding area BLBA, the channel structure CHS can extend in a direction perpendicular to the upper surface of the second substrate 1310 to penetrate the word line 1330, the serial select line, and the ground select line. Each of the channel structures CHS may include a data storage layer, a channel layer, and a buried insulating layer, the channel layer being electrically connected to the first metal layer 1350c and the second metal layer 1360c. For example, the first metal layer 1350c may be a bit line contact, and the second metal layer 1360c may be a bit line (corresponding to...). Figure 5 (BL1 to BL3). In one embodiment, bit line 1360c may extend along a second direction Y parallel to the upper surface of the second substrate 1310.

[0115] exist Figure 7 In the embodiment shown, the region where the channel structure CHS and bit line 1360c are provided can be defined as the bit line bonding region BLBA. In the bit line bonding region BLBA, one of the bit lines 1360c can be electrically connected to a circuit element 1220c that provides a page buffer 1393 in the peripheral circuit region PERI. For example, one of the bit lines 1360c can be connected to upper bonding metals 1371c and 1372c in the peripheral circuit region PERI, and the upper bonding metals 1371c and 1372c can be connected to lower bonding metals 1271c and 1272c, which are connected to the circuit element 1220c of the page buffer 1393.

[0116] In the word line bonding area (WLBA), word lines 1330 may extend along a first direction X parallel to the upper surface of the second substrate 1310 and may be connected to a plurality of cell contact plugs 1341 to 1347 (1340). Word lines 1330 and cell contact plugs 1340 may be connected to each other via pads provided by at least some of the word lines 1330 extending to different lengths along the first direction X. A first metal layer 1350b and a second metal layer 1360b may be sequentially connected to the cell contact plugs 1340 connected to the word lines 1330. In the word line bonding area (WLBA), cell contact plugs 1340 may be connected to the peripheral circuitry area (PERI) via upper bonding metals 1371b and 1372b of the cell region (CELL) and lower bonding metals 1271b and 1272b of the peripheral circuitry area (PERI).

[0117] The cell contact plug 1340 can be electrically connected to circuit element 1220b that provides line decoder 1394 in the peripheral circuitry region PERI. In one embodiment, the operating voltage of circuit element 1220b providing line decoder 1394 can be different from the operating voltage of circuit element 1220c providing page buffer 1393. For example, the operating voltage of circuit element 1220c providing page buffer 1393 can be greater than the operating voltage of circuit element 1220b providing line decoder 1394.

[0118] A common-source contact plug 1380 may be disposed in the external pad bonding region PA. The common-source contact plug 1380 may be made of a conductive material (such as a metal, metal compound, or polysilicon) and may be electrically connected to the common-source wire 1320. A first metal layer 1350a and a second metal layer 1360a may be sequentially stacked on the common-source contact plug 1380. For example, the region where the common-source contact plug 1380, the first metal layer 1350a, and the second metal layer 1360a are disposed may be defined as the external pad bonding region PA.

[0119] Input / output pads 1205 and 1305 can be positioned within the external pad mating area PA. (See reference...) Figure 7 A lower insulating layer 1201 may be formed below the first substrate 1210 to cover the lower surface of the first substrate 1210, and a first input / output pad 1205 may be formed on the lower insulating layer 1201. The first input / output pad 1205 can be connected to at least one of the circuit elements 1220a to 1220c disposed in the peripheral circuit region PERI via a first input / output contact plug 1203, and can be separated from the first substrate 1210 via the lower insulating layer 1201. Furthermore, a side insulating layer may be disposed between the first input / output contact plug 1203 and the first substrate 1210 to electrically isolate the first input / output contact plug 1203 from the first substrate 1210.

[0120] Still refer to Figure 7 An upper insulating layer 1301 may be formed on the second substrate 1310 to cover the upper surface of the second substrate 1310, and a second input / output pad 1305 may be disposed on the upper insulating layer 1301. The second input / output pad 1305 may be connected to at least one of the circuit elements 1220a to 1220c disposed in the peripheral circuit region PERI via a second input / output contact plug 1303.

[0121] According to an embodiment, the second substrate 1310 and the common-source pole 1320 are not disposed in the region where the second input / output contact plug 1303 is provided. Furthermore, according to an embodiment, the second input / output pad 1305 does not overlap with the word line 1330 in the third direction Z. (See also...) Figure 7 The second input / output contact plug 1303 can be separated from the second base 1310 in a direction parallel to the upper surface of the second base 1310, and can penetrate the interlayer insulation layer 1315 of the cell region and connect to the second input / output pad 1305.

[0122] According to embodiments, the first input / output pad 1205 and the second input / output pad 1305 may be selectively formed. For example, according to some embodiments, the non-volatile memory 300 may include only the first input / output pad 1205 disposed on the first substrate 1210, or it may include only the second input / output pad 1305 disposed on the second substrate 1310. Optionally, the non-volatile memory 300 may include both the first input / output pad 1205 and the second input / output pad 1305.

[0123] In each of the outer pad bonding region PA and bit line bonding region BLBA included in each of the cell region CELL and the peripheral circuit region PERI, the metal pattern of the uppermost metal layer may exist as a dummy pattern, or the upper metal layer may be empty.

[0124] In the external pad bonding region PA of the non-volatile memory 300 according to an embodiment of the present disclosure, a lower metal pattern 1273a having the same shape as the upper metal pattern 1372a of the cell region CELL can be formed in the uppermost metal layer of the peripheral circuit region PERI to correspond to the upper metal pattern 1372a formed in the uppermost metal layer of the cell region CELL. According to the embodiment, the lower metal pattern 1273a formed in the uppermost metal layer of the peripheral circuit region PERI is not connected to any individual contact in the peripheral circuit region PERI. Similarly, in the external pad bonding region PA, an upper metal pattern having the same shape as the lower metal pattern of the peripheral circuit region PERI can be formed in the uppermost metal layer of the cell region CELL to correspond to the lower metal pattern formed in the uppermost metal layer of the peripheral circuit region PERI.

[0125] Lower bonding metals 1271b and 1272b can be formed on the second metal layer 1240b of the word line bonding region WLBA. In the word line bonding region WLBA, the lower bonding metals 1271b and 1272b of the peripheral circuit region PERI can be electrically connected to the upper bonding metals 1371b and 1372b of the cell region CELL by bonding method.

[0126] Furthermore, in the bit line bonding region BLBA, an upper metal pattern 1392 having the same shape as the lower metal pattern 1252 of the peripheral circuit region PERI can be formed in the uppermost metal layer of the cell region CELL to correspond to the lower metal pattern 1252 formed in the uppermost metal layer of the peripheral circuit region PERI. According to an embodiment, the contact is not formed on the upper metal pattern 1392 formed in the uppermost metal layer of the cell region CELL.

[0127] Figure 8 and Figure 9 This is a diagram illustrating a method of operating a storage device according to an embodiment of the present disclosure. Figure 10 The logical address ADDR_L region used in an electronic system according to an embodiment of the present disclosure is shown. Figure 11 This is a diagram illustrating a hybrid mapping used together with physical mapping and logical mapping in an electronic system according to embodiments of the present disclosure. Figure 12 It shows the relationship with Figure 11 The mapping table MT corresponds to the mapping.

[0128] Reference Figure 8 and Figure 9 The host sends a command to the memory controller requesting the creation of multiple namespaces (operation S110). See reference... Figure 10According to some embodiments, the logical address ADDR_L region used in an electronic system may include a first namespace NS1, a second namespace NS2, and a third namespace NS3. The logical address region of the first namespace may be the logical address region where sequential writes are performed, the logical address region of the second namespace NS2 may be the logical address region where random writes are performed, and the logical address region of the third namespace NS3 may be a logical address region categorized for other purposes. The logical address region of the first namespace NS1 may be used for sequential write access (such as sequential mode or backup), and the logical address region of the second namespace NS2 may be used for metadata writing or random write access (such as logging).

[0129] The first namespace NS1 may include logical block numbers LBN0 to LBN3, the second namespace NS2 may include logical block numbers LBN4 to LBN7, and the third namespace NS3 may include logical block numbers LBN8 to LBN10. The zeroth logical block number LBN0 may include logical page numbers LPNa to LPNb, the third logical block number LBN3 may include logical page numbers LPNc to LPNd, the fourth logical block number LBN4 may include logical page numbers LPNe to LPNf, the seventh logical block number LBN7 may include logical page numbers LPNg to LPNh, the eighth logical block number LBN8 may include logical page numbers LPNi to LPNj, and the tenth logical block number LBN10 may include logical page numbers LPNk to LPNl. The above-described number and arrangement of logical block numbers and logical page numbers assigned to each namespace are merely examples to illustrate that each namespace includes multiple logical block numbers / logical page numbers, and embodiments of this disclosure are not limited to the above-described numbers or arrangements. The number of logical block numbers / logical page numbers is a natural number of 1 or greater.

[0130] Also refer to Figure 3 Memory controller 200 (see Figure 2 The namespace manager module 221 in the system can receive the inclusion relationship between namespaces and logical block numbers / logical page numbers, as well as commands for requesting the creation of first namespaces NS1 to third namespaces NS3, from the host device 100, and can reflect... Figure 10 The inclusion relationship is used to create the first namespace NS1 to the third namespace NS3 (operation S111).

[0131] The host device 100 sends a physical mapping command for the first namespace NS1 along with a first write command for the first namespace NS1 to the memory controller 200 (operation S120).

[0132] Reference Figure 11 The memory controller 200 physically maps the logical block numbers LBN0 to LBN3 in the first namespace NS1 to the zeroth memory block BLK0 and the first memory block BLK1 (operation S130).

[0133] To perform physical mapping (operation S130), the garbage collection manager module 223 in the memory controller 200 can search for or create multiple free blocks based on the size of the data DATA to be written by the first write command (operation S131). When a physical mapping command is received, if the size of the data that can be accommodated in a free block in an erased state is larger than the size of the data DATA to be written, the garbage collection manager module 223 can search for the zeroth memory block BLK 0 and the first memory block BLK 1 to be physically mapped. When a physical mapping command is received, if the size of the data that can be accommodated in a free block in an erased state is smaller than the size of the data DATA to be written, the garbage collection manager module 223 can perform garbage collection to erase some blocks, thereby additionally creating free blocks.

[0134] The mapping table manager module 224 can physically map logical block numbers LBN0 to LBN3 in the first namespace NS1 to the zeroth memory block BLK0 and the first memory block BLK1, which are free blocks (operation S132).

[0135] In response to the physical mapping command, the mapping table manager module 224 exclusively maps logical block numbers LBN0 to LBN3 in the first namespace NS1 to the zeroth memory block BLK0 and the first memory block BLK1. Therefore, logical block numbers LBN0 to LBN3 can be exclusively mapped to the zeroth memory block BLK0 and the first memory block BLK1.

[0136] Therefore, also refer to Figure 12 The mapping table manager module 224 can prevent the zeroth memory block BLK0 and the first memory block BLK1 from being mapped to other logical block numbers LBN4 to LBN10 (unless the physical mapping is modified), and can store the above mapping information in the address mapping table MT. Figure 3 (225) in the middle.

[0137] According to the embodiment, the mapping table manager module 224 can logically map logical block numbers LBN4 to LBN10 to second memory blocks BLK2 to N-1th memory blocks BLKN-1. The second memory blocks BLK2 to N-1th memory blocks BLKN-1 can be effectively mapped based on the results of garbage collection operations and wear leveling operations. The logical mapping will be described later.

[0138] The number of physically mapped blocks according to the embodiments can be determined by the number of memory cell arrays 310a to 310m. When the non-volatile memory 300 includes a plurality of memory cell arrays 310a to 310m, the memory cell arrays 310a to 310m can operate in parallel according to the embodiments. Therefore, since the zeroth memory block BLK 0 and the first memory block BLK 1 in each of the m memory cell arrays 310a to 310m are physically mapped, the number of physically mapped memory blocks in the non-volatile memory 300 is 2m, which is a multiple of m (where m is a natural number of 1 or greater). However, the number of physically mapped memory blocks in a single memory cell array 310 can vary according to embodiments of the present disclosure. For example, in an embodiment, the number of physically mapped memory blocks in the non-volatile memory 300 can be a positive integer multiple of the memory cell arrays included in the non-volatile memory 300.

[0139] Perform a first write operation on the zeroth memory block BLK 0 and the first memory block BLK 1 (operation S140).

[0140] In order to perform the first write operation (S140), the memory controller 200 sends a first write command for the zeroth memory block BLK 0 and the first memory block BLK 1 to the control logic 350 (operation S141). In response to the first write command (operation S141), the control logic 350 performs the first write operation on the zeroth memory block BLK 0 and the first memory block BLK 1 (operation S142).

[0141] The first write operation (operation S140) can correspond to a sequential write to the first namespace NS1.

[0142] Reference Figure 11 and Figure 12 The memory controller 200 logically maps the logical page numbers in the second namespace NS2 and the third namespace NS3 to the memory pages in the second memory block BLK2 to the (N-1)th memory block BLKN-1 (operation S150).

[0143] Logical mapping can be performed on a wide area, non-exclusively, excluding the physical addresses of the physical mapping, based on the results of garbage collection and wear leveling operations, without receiving separate commands related to mapping attributes from the host device 100. Due to these characteristics, some embodiments can utilize page-by-page mapping instead of block-by-block mapping in the logical mapping. When write commands are received for the second namespace NS2 and the third namespace NS3, random writes can be performed instead of sequential writes.

[0144] For example, the j-th logical page number LPNj included in the third namespace NS3 can be mapped to the a-th physical page number PPNa in the second memory block BLK2, the i-th logical page number LPNi included in the third namespace NS3 can be mapped to the b-th physical page number PPNb in the same second memory block BLK2, and the g-th logical page number LPNg included in the second namespace NS2 can be mapped to the c-th physical page number PPNc in the same second memory block BLK2.

[0145] Then, due to the nature of logical mapping, the above mapping information can be updated through garbage collection and wear leveling operations. Therefore, the mapping information from logical page number LPNi to physical page number PPNb and from logical page number LPNg to physical page number PPNc can be updated through subsequent logical mapping operations. Thus, mapping operations different from the mapping information from logical page number LPNg to physical page number PPNc can be performed.

[0146] The e-th logical page number LPNe in the second namespace NS2 can be mapped to the d-th physical page number PPNd in the third memory block BLK3, the l-th logical page number LPNl in the third namespace NS3 can be mapped to the e-th physical page number PPNe in the same third memory block BLK3, and the f-th logical page number LPNf in the second namespace NS2 can be mapped to the f-th physical page number PPNf in the same third memory block BLK3.

[0147] The kth logical page number LPNk in the third namespace NS3 can be mapped to the gth physical page number PPNg in the (N-1)th memory block BLK N-1, and the hth logical page number LPNh in the second namespace NS2 can be mapped to the hth physical page number PPNh in the same (N-1)th memory block BLK N-1.

[0148] Although in the accompanying drawings, the logical mapping (operation S150) is performed after the physical mapping (operation S130), this is merely an example, and embodiments of this disclosure are not limited to the above mapping order.

[0149] After sending the first write command (operation S120), the host device 100 sends a second write command for the first namespace NS1 to the memory controller 200 (operation S160). Unlike the sending of the first write command (operation S120), a separate mapping operation is not performed.

[0150] A second write operation is performed on memory block BLK0 and memory block BLK1 (operation S170). In some embodiments, the second write operation may be performed based on a second write command and a mapping table. Furthermore, for example, the second write operation may be performed on memory block BLK0 and memory block BLK1, while the mapping information regarding memory block BLK0 and memory block BLK1 may be maintained.

[0151] In order to perform the second write operation (operation S170), an erase operation is performed on the zeroth memory block BLK0 and the first memory block BLK1 (operation S171). In response to the erase operation (operation S171), the control logic 350 performs the second write operation on the zeroth memory block BLK0 and the first memory block BLK1 (operation S172).

[0152] The second write operation (operation S170) can correspond to the sequential write to the first namespace NS1.

[0153] Figure 13 A logical address region used in an electronic system according to an embodiment of the present disclosure is shown. Figure 14 Hybrid mapping used in an electronic system according to embodiments of the present disclosure is illustrated.

[0154] Now refer to Figure 13 and Figure 14 This description describes an electronic system according to embodiments of the present disclosure. The following description will focus on... Figure 10 and Figure 11 The differences in the electronic systems shown are illustrated, and for ease of explanation, further descriptions of the previously described components and technical aspects will be omitted.

[0155] The first namespace NS1 includes the e-th logical page number LPNe and the m-th logical page number LPNm in the fourth logical block number LBN4. Therefore, the first namespace NS1 can include both logical page numbers and logical block numbers.

[0156] Other logical page numbers LPNn and LPNf in the fourth logical block number LBN4 can be included in the second namespace NS2.

[0157] Therefore, when performing physical mapping on the first namespace NS1, the mapping table manager module 224 exclusively maps the e-th logical page number LPNe and the m-th logical page number LPNm in the fourth logical block number LBN4 to the zeroth memory block BLK0 and the first memory block BLK1. Furthermore, in such an embodiment, the logical page numbers LPNn and LPNf in the fourth logical block number LBN4 can be mapped to the d-th physical page number PPNd and the f-th physical page number PPNf of the third memory block BLK3, respectively, and the logical page numbers LPNo and LPNp in the fifth logical block number LBN5 can be mapped to the i-th physical page number PPNi and the j-th physical page number PPNj of the (N-1)-th memory block BLKN-1, respectively.

[0158] Figures 15 to 17 It is a graph used to explain the effects of the electronic system according to embodiments of the present disclosure.

[0159] Figure 15 This is a graph showing the sequential write speed of a storage device 10 that performs physical mapping of the namespace to which sequential writes are applied, as in the mapping table manager module 224 of the current embodiment.

[0160] Figure 16 This is a graph showing the sequential write speed of a storage device that performs garbage collection (GC) and logical mapping on the namespace to which sequential writes are applied.

[0161] Figure 17 This is a graph showing the sequential write speed of a storage device that performs wear leveling (WL) and logical mapping on the namespace to which sequential writes are applied.

[0162] Reference Figure 15 As can be seen, during both the first sequential write and the second sequential write (the operation following the first sequential write), the storage device 10 according to the embodiments of this disclosure is written at a rate higher than the appropriate write speed Va. Therefore, the end time of each of the first sequential write and the second sequential write is a first time T. A .

[0163] Reference Figure 16As can be seen, during sequential writes, the storage device performing logical mapping and garbage collection (GC) is written at a rate lower than the appropriate write speed Va at the first dip (dip) at the start of the first sequential write. This is because time is spent searching for or creating free blocks for garbage collection due to the wide-area mapping characteristics of logical mapping. Furthermore, multiple dips occur in the middle of the second sequential write due to garbage collection operations. Therefore, the end time of each of the first and second sequential writes is lower than... Figure 15 The first time T A The large second time T B .

[0164] Reference Figure 17 As can be seen, the memory device performing logical mapping and wear leveling (WL) during sequential writes repeatedly experiences a second drop during the first sequential write and is written at a rate lower than the appropriate write speed Va. This is because time is spent searching and updating the mapping due to the wide-area mapping characteristics of the logical mapping to evenly adjust the wear of the non-volatile memory. Therefore, the third time T, which is the end time of the first sequential write, is... C The fourth time T, which is the end time of the second sequential write, is compared to the fourth time. D big.

[0165] The storage device 10 of this disclosure performs physical mapping on namespaces that utilize sequential writes. This reduces the time spent searching and updating the mapping for garbage collection (GC) and wear leveling (WL), thereby increasing the speed of sequential write operations.

[0166] Figure 18 This is a block diagram of an electronic system 2 including a storage device 10' according to an embodiment of the present disclosure. Figure 19 The interior of a non-volatile memory according to an embodiment of the present disclosure is schematically shown. Figure 20 This is an exemplary circuit diagram of a portion of a memory cell array according to an embodiment of the present disclosure.

[0167] Now refer to Figures 18 to 20 Electronic system 2 according to embodiments of the present disclosure is described. The following description will focus on... Figure 2 The differences of electronic system 1 shown are omitted for ease of explanation, and further descriptions of the previously described components and technical aspects will be omitted.

[0168] Reference Figures 18 to 20The storage device 10' may include a first non-volatile memory (NVM1) 300a and a second non-volatile memory (NVM2) 300b. According to an embodiment, the first non-volatile memory 300a and the second non-volatile memory 300b may be heterogeneous memories. For example, the first non-volatile memory 300a may be PRAM, and the second non-volatile memory 300b may be flash memory.

[0169] The operation of the first non-volatile memory 300a can be controlled via the first channel CH1, and the operation of the second non-volatile memory 300b can be controlled via the second channel CH2. The memory controller 200 can receive the write command WCMD and the logical address ADDR_L from the host device 100, and write the data DATA into the first non-volatile memory 300a and the second non-volatile memory 300b.

[0170] The memory blocks in the first nonvolatile memory 300a can be physically mapped to Figure 11 or Figure 14 The zeroth memory block BLK 0 and the first memory block BLK 1, and the memory blocks in the second non-volatile memory 300b can be logically mapped to... Figure 11 or Figure 14 The second memory block BLK 2 to the (N-1)th memory block BLK N-1.

[0171] The structure of the second non-volatile memory 300b of storage device 10' can be similar to... Figure 2 The structure corresponds to the non-volatile memory 300. Furthermore, Figure 18 The host memory 140 and file system 141 can be respectively connected to Figure 2 The host memory 120 and file system 121 are basically the same or similar.

[0172] Reference Figure 19 and Figure 20 The structure of the first non-volatile memory 300a will be described. The first non-volatile memory 300a may include zeroth non-volatile memory blocks BLK'0 to M-1th non-volatile memory blocks BLK'M-1. The zeroth non-volatile memory blocks BLK'0 to M-1th non-volatile memory blocks BLK'M-1 may be spaced apart from each other in a first direction X and / or a second direction Y. Each of the zeroth non-volatile memory blocks BLK'0 to M-1th non-volatile memory blocks BLK'M-1 includes a plurality of memory cells.

[0173] The structure of the zeroth nonvolatile memory block BLK'0 will be described by way of example. It will be understood that the description of the zeroth nonvolatile memory block BLK'0 also applies to other nonvolatile memory blocks. The zeroth nonvolatile memory block BLK'0 may include, for example, PRAM cells.

[0174] The zeroth non-volatile memory block BLK'0 can be a 2D memory. If the zeroth non-volatile memory block BLK'0 includes multiple layers, then the zeroth non-volatile memory block BLK'0 can be a 3D memory.

[0175] The zeroth nonvolatile memory block BLK'0 may include multiple word lines WL0 to WLn, multiple bit lines BL0 to BLm, and multiple memory cells MC. The number of word lines WL, the number of bit lines BL, and the number of memory cells MC may vary according to embodiments of this disclosure. A group of memory cells that can be accessed simultaneously via the same word line may be defined as a page.

[0176] In the zeroth nonvolatile memory block BLK'0 according to an embodiment of the present disclosure, each of the memory cells MC may include a variable resistance element R and a selection element S. Here, the variable resistance element R may be referred to as a variable resistor (or variable resistive material), and the selection element S may be referred to as a switching element.

[0177] According to the embodiment of the present disclosure, in the memory block BLK'0, the selection element S can be a two-way threshold switch (OTS) selector, the OTS selector includes such as GeSe, GeS, AsSe, AsTe, AsS, SiTe, SiSe, SiS, GeAs, SiAs, SnSe, SnTe, GeAsT e、GeAsSe、AlAsTe、AlAsSe、SiAsSe、SiasTe、GeSeTe、GeSeSb、GaAsSe、GaAsTe、InAsSe、InAsTe、SnAsSe TeSb, GeSiSeSb, GeSiTeSb, GeSeTeBi, GeSiseBi, GeSiTeBi, GeAsSeSb, GeAsTeSb, GeAsteBi, GeAsSeBi, GeAsSeIn, GeAsseGa, GeAsseAl, GeAsSeTl, GeAsSeSn, GeAsSeZn, GeAsteIn, GeAsteGa, GeAsteAl, GeAsteTl, GeAsteSn, GeAsteZn, GeSiAsseTe, GeAsSeTeS, GeSiAsseSe, GeSiAsseTe, GeSi AsSeP、GeSiAsTeP、GeAsSeTeP、GeSiAsSeIn、GeSiAsSeGa、GeSiAsSeAl、GeSiAsSeTl、GeSiAsSeZn、GeSiAsSeSn、GeSiAsTeIn、GeSiAsTeGa、GeSiAsTeAl GeSiAsTeTl eSAL, GeAsSeSTl, GeAsSeSZn, GeAsSeSSn, GeAsTeSIN, GeAsTeSga, GeAsTeSAL, GeAsTeSTl, GeAsTeSZn, GeAsTeSSn, GeAsSeInGa, GeAsSeInAl, GeAsSeInTl, GeAsSeInZn, GeAsSeInSn, GeAsseGaAl, GeAsseGaTl, GeAsseGaZn, GeAsseGaSn, GeAsseAlTl, GeAsseAlZn, GeAsSEAlSn, GeAsSeTlZn, GeAsSeTlSn,GeAsSeZnSn, GeSiAsSeTeS, GeSiAsSeTeIn, GeSiAsSeTeGa, GeSiAsSeTeAl, GeSiAsSeTeTl, GeSiAsSeTeZn, G eSiAsSeTeSn, GeSiAsSeTeP, GeSiAsSeSIn, GeSiAsSeSGa, GeSiAsSeSAl, GeSiAsSeSTl, GeSiAsSeSZn, GeSiA sSeSSn, GeAsSeTeSIn, GeAsSeTeSGa, GeAsSeTeSAl, GeAsSeTeSTl, GeAsSeTeSZn, GeAsSeTeSSn, GeAsSeTePI n, GeAsSeTePGa, GeAsSeTePAl, GeAsSeTePTl, GeAsSeTePZn, GeAsSeTePSn, GeSiAsSeInGa, GeSiAsSeInAl, Ge SiAsSeInTl, GeSiAsSeInZn, GeSiAsSeInSn, GeSiAsSeGaAl, GeSiAsSeGaTl, GeSiAsSeGaZn, GeSiAsSeGaSn, GeSiAsSeAlSn, GeAsSeTeInGa, GeAsSeTeInAl, GeAsSeTeInTl, GeAsSeTeInZn, GeAsSeTeInSn, GeAsSeTeGaAl , GeAsSeTeGaTl, GeAsSeTeGaZn, GeAsSeTeGaSn, GeAsSeTeAlSn, GeAsSeSInGa, GeAsSeSInAl, GeAsSeSInTl, Compounds such as GeAsSeSInZn, GeAsSeSInSn, GeAsSeSGaAl, GeAsSeSGaTl, GeAsSeSGaZn, GeAsSeSGaSn or GeAsSeSAlSn are exemplified. ,

[0178] For example, the variable resistor element R can be connected between one of the bit lines BL0 to BLm and the selection element S, and the selection element S can be connected between the variable resistor element R and one of the word lines WL0 to WLn.

[0179] However, the embodiments disclosed herein are not limited thereto, and in some embodiments, the selection element S may also be connected between one of the bit lines BL0 to BLm and the variable resistor element R, and the variable resistor element R may be connected between the selection element S and one of the word lines WL0 to WLn.

[0180] The selector element S can be connected between any one of the word lines WL0 to WLn and the variable resistor element R, and the current supply to the variable resistor element R can be controlled according to the voltage applied to the connected word line and bit line.

[0181] As is conventional in the field of this disclosure, embodiments may be described and illustrated in the accompanying drawings as functional blocks, units, and / or modules. Those skilled in the art will understand that these blocks, units, and / or modules are physically implemented via electronic (or optical) circuitry (such as logic circuits), discrete components, microprocessors, hardwired circuitry, memory elements, wiring connections, etc., which may be formed using semiconductor-based manufacturing techniques or other manufacturing techniques. Where blocks, units, and / or modules are implemented via microprocessors or the like, they may be programmed using software (e.g., microcode) to perform the various functions discussed herein and may optionally be driven by firmware and / or software. Alternatively, each block, unit, and / or module may be implemented via dedicated hardware, or as a combination of dedicated hardware for performing some functions and processors (one or more programmed microprocessors and associated circuitry) for performing other functions.

[0182] In embodiments of this disclosure, a three-dimensional (3D) memory array is provided. The 3D memory array is monolithically formed in one or more physical levels of an array of memory cells having active regions disposed above a silicon substrate and circuitry associated with the operation of those memory cells, regardless of whether such associated circuitry is above or within such a substrate. The term "monolithic" means that each layer of the array is deposited directly on each layer of the lower level of the array. In embodiments of this disclosure, the 3D memory array includes vertical NAND strings oriented vertically such that at least one memory cell is situated above another memory cell. The at least one memory cell includes a charge trapping layer. Suitable configurations for three-dimensional memory arrays are described by reference to the following patent documents contained herein, wherein the three-dimensional memory array is configured as multiple levels and word lines and / or bit lines are shared between levels: U.S. Patent Nos. 7,679,133, 8,553,466, 8,654,587, 8,559,235, and 2011 / 0233648.

[0183] Although this disclosure has been specifically shown and described with reference to embodiments thereof, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of this disclosure as defined by the appended claims.

Claims

1. A multi-namespace storage device, the multi-namespace storage device comprising: The non-volatile memory includes a first memory block and a second memory block that is different from the first memory block; as well as The memory controller receives commands from the host to request the creation of a first namespace and a second namespace, and receives physical mapping commands to instruct the physical mapping of the first namespace, wherein the first namespace includes a first logical block number, and the second namespace includes a first logical page number not included in the first logical block number. In response to a physical mapping command, the memory controller performs a first mapping operation by mapping a first logical block number to a first memory block, and performs a second mapping operation by mapping a first logical page number to a first memory page included in a second memory block. The first namespace includes a second logical page number that is not included in the first logical block number, and the memory controller performs a third mapping operation by mapping the second logical page number to the first memory block together with the first mapping operation.

2. The multi-namespace storage device according to claim 1, wherein, The first memory block is exclusively associated with the first logical block number through the first mapping operation.

3. The multi-namespace storage device according to claim 2, wherein, The second mapping operation is not performed on the first memory block.

4. The multi-namespace storage device according to claim 1, wherein, The first logic block number includes logic block number 1_0 to logic block number 1_N-1, and the first memory block includes memory block 1_0 to memory block 1_M-1, where N and M are natural numbers equal to 1 or greater.

5. The multi-namespace storage device according to claim 4, wherein, Non-volatile memory consists of m memory arrays, where M is a positive integer multiple of m.

6. The multi-namespace storage device according to claim 1, wherein, When the memory controller receives a physical mapping command, the first memory block is in an erase state.

7. The multi-namespace storage device according to claim 1, wherein, The first mapping operation includes an erase operation performed on the first memory block.

8. The multi-namespace storage device according to claim 1, wherein, The memory controller receives from the host a first write command for a first logical block number and a second write command for a first logical page number. The first write command is executed as a sequential write to the first memory block, and the second write command is executed as a random write to the first memory page.

9. The multi-namespace storage device according to any one of claims 1 to 8, wherein, The memory controller receives a command to request the creation of a third namespace including a third logical page number, and in response to the physical mapping command, the memory controller performs a fourth mapping operation by mapping the third logical page number to a second memory page included in the second memory block.

10. A multi-namespace electronic system, the multi-namespace electronic system comprising: Multiple non-volatile memories, including a first non-volatile memory and a second non-volatile memory; A memory controller that controls the plurality of non-volatile memories; as well as The host connects to the memory controller and sends commands to request the creation of a first namespace and a second namespace. The first namespace includes a first logical block number, and the second namespace includes a first logical page number not included in the first logical block number. Specifically, the host sends a physical mapping command to instruct the physical mapping of the first namespace, and the memory controller, in response to the physical mapping command, performs a first mapping operation by mapping a first logical block number to a first memory block in the first non-volatile memory, and performs a second mapping operation by mapping a first logical page number to a first memory page included in the second non-volatile memory. The first namespace includes a second logical page number that is not included in the first logical block number, and the memory controller performs a third mapping operation by mapping the second logical page number to the first memory block together with the first mapping operation.

11. The multi-namespace electronic system according to claim 10, wherein, The first type of non-volatile memory is phase-change random access memory, and the second type of non-volatile memory is flash memory.

12. The multi-namespace electronic system according to claim 10, wherein, The first memory block is exclusively associated with the first logical block number through the first mapping operation.

13. The multi-namespace electronic system according to any one of claims 10 to 12, wherein, The memory controller receives a command to request the creation of a third namespace that includes a third logical page number not included in the first logical block number, and in response to the physical mapping command, the memory controller performs a fourth mapping operation by mapping the third logical page number to a second memory page included in the second non-volatile memory.

14. The multi-namespace electronic system according to claim 13, wherein, The fourth mapping operation is performed after the second mapping operation, and the second memory page and the first memory page are included in the same memory block of the second non-volatile memory, which is different from the first memory block.

15. A method of operating a multi-namespace storage device, the method comprising: Commands for requesting the creation of a first namespace and a second namespace are sent to the memory controller. The first namespace includes a first logical block number, and the second namespace includes a first logical page number that is not included in the first logical block number. The first write command for the first logical block number is sent together with the physical mapping command for commanding the physical mapping of the first namespace to the memory controller. In response to a physical mapping command, the first mapping information from the first logical block number to the first memory block corresponding to the first logical block number is stored in a mapping table; In response to the first write command, a first write operation is performed on the first memory block; After sending the first write command, a second write command for the first logical block number is sent to the memory controller; Based on the second write command and the mapping table, a second write operation is performed on the first memory block; In response to a physical mapping command, a first mapping operation is performed by mapping a first logical block number to a first memory block; In response to a physical mapping command, a second mapping operation is performed by mapping a first logical page number to a first memory page included in a second memory block, the second memory block being different from the first memory block, wherein the first namespace includes second logical page numbers not included in the first logical block number; as well as The third mapping operation is performed by mapping the second logical page number to the first memory block in conjunction with the first mapping operation.

16. The method according to claim 15, wherein, The second write operation is performed while the first mapping information is preserved.

17. The method according to claim 15, wherein, The first write operation and the second write operation are performed as sequential writes to the first memory block.

Citation Information

Patent Citations

  • Color-convertible microlens array with fine printing of quantum dot / polymer composite and manufaturing method thereof

    KR1020200137977A

  • Three-Dimensional Semiconductor Memory Devices And Methods Of Fabricating The Same

    US20110233648A1

  • Vertical-type non-volatile memory devices

    US7679133B2

  • Non-volatile memory device, erasing method thereof, and memory system including the same

    US8553466B2

  • Nonvolatile memory device, operating method thereof and memory system including the same

    US8559235B2