Memory device
By dividing molecular memory banks in a volatile memory device and optimizing the allocation of word lines and column selection lines, the problems of data loss and chip size overhead when the power supply is interrupted are solved, and efficient data allocation and stable output are achieved.
Patent Information
- Application Number
- CN202410636486.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-09-14
- Filing Date
- 2024-05-22
- Publication Date
- 2024-11-26
AI Technical Summary
Existing volatile memory devices lose data when power is interrupted, and dynamic random access memory (DRAM) has overhead in chip size, making it difficult to meet the requirements of efficient data allocation.
By dividing a molecular memory bank in the memory bank and selecting word lines and column selection lines using row decoder and column decoder respectively, the simultaneous reading and writing of normal data and metadata is achieved, and the chip size overhead is reduced. Share GIO lines between different sub-banks to improve data output efficiency.
It realizes that without increasing the chip size, meets the requirements of efficient data allocation, ensures data stability and efficiency, and reduces power consumption.
Smart Images

Figure CN119028394A_ABST
Abstract
Description
[0001] This application claims the priority of Korean Patent Application No. 10-2023-0066576 filed on May 23, 2023, in the Korean Intellectual Property Office, and Korean Patent Application No. 10-2023-0122763 filed on September 14, 2023, in the Korean Intellectual Property Office, the disclosures of which are incorporated herein by reference in their entirety. Technical Field
[0002] The present disclosure relates to memory devices. Background Art
[0003] Semiconductor memory devices can be classified into volatile memory devices and nonvolatile memory devices. When the power supply of the volatile memory device is interrupted, the volatile memory device loses its stored data. Dynamic random access memory (DRAM) is a type of volatile memory device and is used in various fields such as mobile systems, servers, and graphics devices. Summary of the invention
[0004] A volatile memory device for allocating specific data is described.
[0005] An example memory device includes a memory bank connected to a plurality of word lines and a plurality of column select lines (CSLs). Among the plurality of word lines, every r-th word line (where r is a positive integer) in a column direction may be allocated for metadata.
[0006] An example memory device includes: a memory bank connected to a plurality of word lines and a plurality of column select lines (CSLs); a row decoder connected to the plurality of word lines and extending in a column direction; and a column decoder connected to the plurality of CSLs and extending in a row direction. Among the plurality of word lines, every r-th word line (where r is a positive integer) in the column direction may be allocated for metadata.
[0007] An example memory device includes: a sub-memory body, which is divided in a row direction and includes multiple subsets each divided in the row direction; a plurality of word lines, which extend in the row direction and are connected to the sub-memory bodies, wherein, among the plurality of word lines, every rth word line (where r is a positive integer) in the column direction is allocated for metadata; and a plurality of column selection line (CSL) subsets, which extend in the column direction and are connected to the sub-memory bodies. BRIEF DESCRIPTION OF THE DRAWINGS
[0008] The above and other aspects, features and advantages of the present disclosure will be more clearly understood from the following detailed description taken in conjunction with the accompanying drawings.
[0009] Figure 1 is a diagram illustrating an example memory system.
[0010] Figure 2 is a plan view of an example memory device.
[0011] Figure 3 and Figure 4 is a diagram illustrating a read operation of a memory cell.
[0012] Figure 5 and Figure 6 is a diagram illustrating a word line allocation method.
[0013] Figure 7 is a diagram illustrating example sub-banks.
[0014] Figure 8 It is shown Figure 7 FIG. 1 is a diagram of an example of area “A”.
[0015] Fig. 9 and Fig.10 is a diagram showing column selection signals for normal data and metadata.
[0016] Fig.11 and Fig.12 is a diagram showing an assignment relationship between a first word line and a column selection line (CSL) when the first sub-bank is a normal-side sub-bank.
[0017] Fig.13 and Fig.14 is a diagram showing an allocation relationship between a second word line and a CSL when a first sub-bank is a normal-side sub-bank.
[0018] Fig.15 and Fig.16 is a diagram showing an allocation relationship between a last word line and a CSL when a first sub-bank is a normal-side sub-bank.
[0019] Fig.17 and Fig.18 is a diagram showing an allocation relationship between a first word line and a CSL when a second sub-bank is a normal-side sub-bank.
[0020] Fig.19 and Fig. 20 is a diagram showing an allocation relationship between a second word line and a CSL when the second sub-bank is a normal-side sub-bank.
[0021] Fig.21 and Fig. 22 is a diagram showing an allocation relationship between a last word line and a CSL when the second sub-bank is a normal-side sub-bank.
[0022] Fig.23 and Fig.24is a diagram showing an allocation relationship between a first word line and a CSL when the first sub-bank is a normal-side sub-bank.
[0023] Fig.25 and Fig.26 is a diagram showing an allocation relationship between a second word line and a CSL when a first sub-bank is a normal-side sub-bank.
[0024] Fig. 27 and Fig.28 is a diagram showing an allocation relationship between a last word line and a CSL when a first sub-bank is a normal-side sub-bank.
[0025] Fig.29 and Fig.30 is a diagram showing an allocation relationship between a first word line and a CSL when a second sub-bank is a normal-side sub-bank.
[0026] Fig.31 and Fig.32 is a diagram showing an allocation relationship between a second word line and a CSL when the second sub-bank is a normal-side sub-bank.
[0027] Fig.33 and Fig.34 is a diagram showing an allocation relationship between a last word line and a CSL when the second sub-bank is a normal-side sub-bank.
[0028] Fig.35 is a diagram illustrating a sub-bank configuration according to example embodiments.
[0029] Fig.36 It is shown Fig.35 Schematic diagram of word line activation operation in a sub-memory configuration. DETAILED DESCRIPTION
[0030] Hereinafter, example embodiments will be described with reference to the accompanying drawings.
[0031] Figure 1 is a diagram illustrating an example memory system.
[0032] Reference Figure 1 , a memory system 100 according to example embodiments may include a memory controller 110 and a memory device 120 .
[0033] The memory controller 110 may control the overall operation of the memory system 100, and may control data exchange between the memory device 120 and a host device connected to the memory system 100. For example, the memory controller 110 may control the memory device 120 to write or read data based on a request from the host device.
[0034] The memory controller 110 may communicate with the memory device 120 through a memory interface, or communicate with the host device through a host interface. Therefore, the memory controller 110 may mediate a signal between the host device and the memory device 120. The memory controller 110 may control the memory device 120 based on a command CMD for controlling the memory device 120. For example, the memory device 120 may include a dynamic random access memory (DRAM), a fourth generation double data rate (DDR4) synchronous DRAM (SDRAM), DDR5 SDRAM, DDR6 SDRAM, low power DDR4 (LPDDR4) SDRAM, LPDDR5 SDRAM, LPDDR6 SDRAM, etc. However, example embodiments are not limited thereto, and the memory device 120 may include a non-volatile memory device. However, in one example, the memory device 120 is a volatile memory.
[0035] The memory controller 110 may transmit the above-mentioned command CMD, the clock signal CLK, and the address ADDR to the memory device 120. The memory controller 110 may provide data DQ to the memory device 120, and may receive data DQ from the memory device 120. The memory device 120 may include a memory cell array (MCA) 130 storing the data DQ, a control logic circuit 140, a data input / output (I / O) buffer 150, and the like.
[0036] The memory cell array 130 may include a plurality of memory cells. Each memory cell may store data (e.g., 1 bit). The memory cell array 130 may include a plurality of word lines and a plurality of column select lines (CSLs), and a plurality of memory cells may be connected to each word line and each CSL. In this case, the memory cells connected to the word lines may be referred to as rows, and the memory cells selected by the CSLs may be referred to as columns.
[0037] A portion of the word lines may be allocated for metadata. Metadata may be defined as data for improving the performance of the memory device 120 and enhancing the security of the memory device 120. In addition to the word lines WL_M allocated for metadata, the remaining word lines WL_N may be allocated for normal data. Normal data may be defined as data other than metadata.
[0038] According to various embodiments, a ratio of normal data to metadata accessed by the memory device 120 may be required. For example, a required ratio of normal data to metadata accessed by the memory device 120 (hereinafter, a required normal / meta ratio) may be set to n:1 (where n is a positive integer). For example, n may be 8 or 16, but example embodiments are not limited thereto. For example, in the case of n=8, when 64 bytes of normal data are accessed, 8 bytes of metadata may need to be accessed.
[0039] One or more bit lines may be connected to the CSL. Therefore, when a single CSL is selected (e.g., when a single column is selected), all one or more bit lines connected to the selected CSL may be selected, and data in units of burst lengths may be simultaneously input and output from the one or more selected bit lines. For example, eight bit lines may be connected to a single CSL, but example embodiments are not limited thereto.
[0040] The control logic circuit 140 may receive a command CMD and an address ADDR from the memory controller 110. The control logic circuit 140 may control the memory cell array 130 based on the command CMD and the address ADDR. For example, the control logic circuit 140 may decode the command CMD and generate a control signal corresponding to the decoded command CMD. In addition, the control logic circuit 140 may generate an internal command (CMD) signal (such as a refresh signal, an activation signal, a precharge signal, a read signal, or a write signal). In addition, the control logic circuit 140 may decode the address ADDR and select or activate a word line and CSL corresponding to the decoded address ADDR.
[0041] The data input / output buffer 150 may provide normal data and / or metadata to the memory cell array 130 based on the clock signal CLK when a write operation is performed, or may provide normal data and / or metadata provided from the memory cell array 130 to the memory controller 110 based on the clock signal CLK when a read operation is performed.
[0042] According to various embodiments, the memory system 100, the memory controller 110 and the memory device 120 included in the memory system 100 may operate in a metadata mode. The metadata mode may be an operation mode in which metadata is input or output. When operating in the metadata mode, according to various embodiments to be described below ( Figures 2 to 36 ), the memory system 100 may perform a write or read operation based on the word line WL_M allocated for metadata.
[0043] For example, the memory controller 110 and the control logic circuit 140 may control the memory device 120 to simultaneously write or read normal data and metadata through a word line WL_N allocated to normal data and a word line WL_M allocated to metadata.
[0044] In one example embodiment, the memory system 100 may turn off the metadata mode and operate in the normal mode. In the normal mode, the word line WL_M that has been allocated for metadata in the metadata mode may also be allocated for normal data. Therefore, in the normal mode, the memory system 100 may activate at least a portion of the plurality of word lines included in the memory device 120 to write normal data to the memory device 120 or read normal data from the memory device 120. In addition, the operation of the memory system 100 in the normal mode may comply with the operation of DRAM, DDR4, SDRAM, DDR5 SDRAM, DDR6 SDRAM, LPDDR4 SDRAM, LPDDR5 SDRAM, or LPDDR6 SDRAM.
[0045] According to the above-described embodiments, a portion of a word line connected to the memory cell array 130 included in the memory device 120 may be allocated for, for example, metadata. For example, in terms of a row, a portion of a carved row may be used for metadata. When an additional register or line (e.g., a global input / output (GIO) line, etc.) is allocated for metadata, overhead may occur due to chip size. However, according to example embodiments, a portion of an existing word line may be allocated for metadata to reduce overhead occurring due to chip size.
[0046] Figure 2 is a plan view of a memory device according to example embodiments.
[0047] Reference Figure 2 , the memory device 120 may include a memory body unit BU and a peripheral circuit region PERI.
[0048] A plurality of memory cell units BU (also referred to as "bank groups") may be provided according to the capacity of the memory device 120. A portion and a remaining portion of the plurality of memory cell units BU may be arranged in the row direction d2, wherein the peripheral circuit region PERI is placed between a portion and a remaining portion of the plurality of memory cell units BU. Each of the memory cell units BU may include a plurality of memory cells. Each of the plurality of memory cells may include a plurality of matrices including a plurality of memory cells.
[0049] According to example embodiments, each of the plurality of memory banks may include a plurality of sub-memory banks. The plurality of sub-memory banks included in each memory bank may correspond to the same memory bank address. Figure 2In the following embodiments, an example in which two sub-memory bodies are included in a single memory body will be described, but the example embodiments are not limited thereto. A plurality of sub-memory bodies may be arranged in a row direction d2 within a single memory body, wherein row decoders RD1 and RD2 are placed between the plurality of sub-memory bodies. For example, a first memory body B1 may include a 1-1th sub-memory body SB1-1 and a 1-2th sub-memory body SB1-2. The 1-1th sub-memory body SB1-1 and the 1-2th sub-memory body SB1-2 may be arranged in a row direction d2, wherein row decoders RD1 and RD2 are placed between the 1-1th sub-memory body SB1-1 and the 1-2nd sub-memory body SB1-2. In addition, a second memory body B2 arranged in a column direction d1 with the first memory body B1 may include a 2-1st sub-memory body SB2-1 and a 2-2nd sub-memory body SB2-2. The 2-1st sub-bank SB2-1 and the 2-2nd sub-bank SB2-2 may be arranged in the row direction d2 with the row decoders RD1 and RD2 interposed between the 2-1st sub-bank SB2-1 and the 2-2nd sub-bank SB2-2.
[0050] The row decoders RD1 and RD2 may extend in the column direction d1 and may be set in a number corresponding to the number of memory banks included in a single memory bank unit BU. According to an example embodiment, the row decoders RD1 and RD2 may select word lines connected to sub-memory banks included in different memory banks based on decoding a row address. For example, the first row decoder RD1 may select a word line connected to the 1-1 sub-memory bank SB1-1 and the 2-1 sub-memory bank SB2-1, and the second row decoder RD2 may select a word line connected to the 1-2 sub-memory bank SB1-2 and the 2-2 sub-memory bank SB2-2.
[0051] The column decoders CD1 and CD2 may extend in the row direction d2 and may be provided in a number corresponding to the number of memory banks included in a single memory bank unit BU. According to example embodiments, the column decoders CD1 and CD2 may select CSLs connected to sub-memory banks included in different memory banks based on decoding a column address. For example, the first column decoder CD1 may select CSLs connected to the 1-1 sub-memory bank SB1-1 and the 2-1 sub-memory bank SB2-1, and the second column decoder CD2 may select CSLs connected to the 1-2 sub-memory bank SB1-2 and the 2-2 sub-memory bank SB2-2.
[0052] Figure 3 and Figure 4 is a diagram illustrating an example read operation of a memory cell according to various embodiments.
[0053] Reference Figure 3, a portion of the word line connected to the 1-1th sub-storage body SB1-1 can be used as a normal data word line WL_N, and a portion of the word line connected to the 1-2nd sub-storage body SB1-2 can be used as a metadata word line WL_M. In this case, the metadata word line WL_M of the 1-2nd sub-storage body SB1-2 can be a metadata word line WL_M corresponding to the normal data word line WL_N of the 1-1st sub-storage body SB1-1, and a portion of the memory cell connected to the metadata word line WL_M of the 1-2nd sub-storage body SB1-2 can be used to store metadata corresponding to normal data stored in the memory cell connected to the normal data word line WL_N of the 1-1st sub-storage body SB1-1. At the same time, a portion of the word line connected to the 1-2nd sub-storage body SB1-2 can be used as a normal data word line, and a portion of the word line connected to the 1-1st sub-storage body SB1-1 can be used as a metadata word line. In this case, the metadata word line of the 1-1th sub-storage body SB1-1 is a metadata word line corresponding to the normal data word line of the 1-2th sub-storage body SB1-2, and a portion of the memory cells connected to the metadata word line of the 1-1th sub-storage body SB1-1 can be used to store metadata corresponding to normal data stored in the memory cells connected to the normal data word line of the 1-2 sub-storage body SB1-2.
[0054] according to Figure 3In an example embodiment, the first memory bank B1 may include a plurality of sub-memory banks that do not share a GIO: a 1-1th sub-memory bank SB1-1 and a 1-2th sub-memory bank SB1-2. Therefore, a metadata word line WL_M corresponding to a normal data word line WL_N of the 1-1th sub-memory bank SB1-1 may be allocated to a 1-2th sub-memory bank SB1-2 that does not share a GIO with the 1-1th sub-memory bank SB1-1. In addition, a metadata word line corresponding to a normal data word line of the 1-2th sub-memory bank SB1-2 may be allocated to the 1-1th sub-memory bank SB1-1 that does not share a GIO with the 1-2th sub-memory bank SB1-2. Therefore, when normal data is written or read in the 1-1st sub-storage body SB1-1, metadata corresponding to the normal data can be simultaneously written in the metadata word line WL_M of the 1-2nd sub-storage body SB1-2 corresponding to the normal data word line WL_N of the 1-1st sub-storage body SB1-1 or read from the metadata word line WL_M of the 1-2nd sub-storage body SB1-2 corresponding to the normal data word line WL_N of the 1-1st sub-storage body SB1-1. Conversely, when normal data is written or read in the 1-2nd sub-storage body SB1-2, metadata corresponding to the normal data of the 1-2nd sub-storage body SB1-2 can be simultaneously written in the metadata word line of the 1-1st sub-storage body SB1-1 corresponding to the normal data word line of the 1-2nd sub-storage body SB1-2 or read from the metadata word line of the 1-1st sub-storage body SB1-1 corresponding to the normal data word line of the 1-2nd sub-storage body SB1-2.
[0055] According to an example embodiment, normal data and metadata corresponding to the normal data may be simultaneously written in the first memory bank B1. When a read operation is performed on the normal data ND and the metadata MD written in the first memory bank B1, the metadata MD and the normal data ND may be simultaneously read through the two word lines WL_M and WL_N by activating the two word lines WL_M and WL_N for each sub-memory bank (each of the 1-1 sub-memory bank SB1-1 and the 1-2 sub-memory bank SB1-2). For example, the first row decoder RD1 and the second row decoder RD2 may simultaneously select the normal data word line WL_N and the metadata word line WL_M, respectively. In addition, a specific CSL may be selected by the first column decoder CD1 and the second column decoder CD2.
[0056] According to an example embodiment, a write operation of normal data and metadata corresponding to the normal data may be performed simultaneously. When a write operation of normal data ND and metadata MD is performed in the first memory bank B1 (each of the sub-memory banks (each of the 1-1 sub-memory bank SB1-1 and the 1-2 sub-memory bank SB1-2)), metadata MD and normal data ND may be written simultaneously through two word lines WL_M and WL_N by activating both word lines WL_M and WL_N. For example, the first row decoder RD1 and the second row decoder RD2 may respectively select the normal data word line WL_N and the metadata word line WL_M at the same time. In addition, a specific CSL may be selected by the first column decoder CD1 and the second column decoder CD2.
[0057] Then, the data on the selected word line and CSL can be read or written by the GIO line connected to each sub-memory bank. The GIO can extend in the column direction d1 and be spaced apart in the row direction d2. According to an example embodiment, the first GIO GIO1 can be configured to be shared with the 1-1 sub-memory bank SB1-1 of the first memory bank B1 and the 2-1 sub-memory bank SB2-1 of the second memory bank B2, and the second GIO GIO2 can be configured to be shared with the 1-2 sub-memory bank SB1-2 of the first memory bank B1 and the 2-2 sub-memory bank SB2-2 of the second memory bank B2. For example, sub-memory banks belonging to different memory banks can be configured to share the same GIO. Sub-memory banks belonging to different memory banks can share the same GIO so that a single GIO can be used for both read operations and write operations of different sub-memory banks.
[0058] Reference Figure 4, a portion of the word line connected to the 2-1st sub-storage body SB2-1 can be used as a normal data word line WL_N, and a portion of the word line connected to the 2-2nd sub-storage body SB2-2 can be used as a metadata word line WL_M. In this case, the metadata word line WL_M of the 2-2nd sub-storage body SB2-2 can be a metadata word line corresponding to the normal data word line WL_N of the 2-1st sub-storage body SB2-1, and a portion of the memory cell connected to the metadata word line WL_M of the 2-2nd sub-storage body SB2-2 can be used to store metadata corresponding to normal data stored in the memory cell connected to the normal data word line WL_N of the 2-1st sub-storage body SB2-1. At the same time, a portion of the word line connected to the 2-2nd sub-storage body SB2-2 can be used as a normal data word line, and a portion of the word line connected to the 2-1st sub-storage body SB2-1 can be used as a metadata word line. In this case, the metadata word line of the 2-1st sub-storage body SB2-1 can be a metadata word line corresponding to the normal data word line of the 2-2nd sub-storage body SB2-2, and a portion of the memory cells connected to the metadata word line of the 2-1st sub-storage body SB2-1 can be used to store metadata corresponding to normal data stored in the memory cells connected to the normal data word line of the 2-2nd sub-storage body SB2-2.
[0059] according to Figure 4 In an example embodiment, the second memory bank B2 may include a plurality of sub-memory banks that do not share a GIO: a 2-1st sub-memory bank SB2-1 and a 2-2nd sub-memory bank SB2-2. Therefore, a metadata word line WL_M corresponding to a normal data word line WL_N of the 2-1st sub-memory bank SB2-1 may be allocated to a 2-2nd sub-memory bank SB2-2 that does not share a GIO with the 2-1st sub-memory bank SB2-1. In addition, a metadata word line corresponding to a normal data word line of the 2-2nd sub-memory bank SB2-2 may be allocated to the 2-1st sub-memory bank SB2-1 that does not share a GIO with the 2-2nd sub-memory bank SB2-2. Therefore, when normal data is written or read in the 2-1st sub-storage body SB2-1, metadata corresponding to the normal data can be simultaneously written in the metadata word line WL_M of the 2-2nd sub-storage body SB2-2 corresponding to the normal data word line WL_N of the 2-1st sub-storage body SB2-1 or read from the metadata word line WL_M of the 2-2nd sub-storage body SB2-2 corresponding to the normal data word line WL_N of the 2-1st sub-storage body SB2-1. Conversely, when normal data is written or read in the 2-2nd sub-storage body SB2-2, metadata corresponding to the normal data can be simultaneously written in the metadata word line in the 2-1st sub-storage body SB2-1 corresponding to the normal data word line of the 2-2nd sub-storage body SB2-2 or read from the metadata word line in the 2-1st sub-storage body SB2-1 corresponding to the normal data word line of the 2-2nd sub-storage body SB2-2.
[0060] According to example embodiments, normal data and metadata corresponding to the normal data may be simultaneously written in the second memory bank B2. When a read operation is performed on the normal data ND and metadata MD written in the second memory bank B2, the normal data ND and metadata MD may be simultaneously read through the two word lines WL_M and WL_N by activating the two word lines WL_M and WL_N for each sub-memory bank (each of the 2-1st sub-memory bank SB2-1 and the 2-2nd sub-memory bank SB2-2).
[0061] According to an example embodiment, a write operation may be performed on normal data and metadata corresponding to the normal data at the same time. When a write operation on normal data ND and metadata MD is performed in the second storage body B2, normal data ND and metadata MD may be written simultaneously through two word lines WL_M and WL_N by activating the two word lines WL_M and WL_N for each sub-storage body (each of the 2-1st sub-storage body SB2-1 and the 2-2nd sub-storage body SB2-2). For example, the first row decoder RD1 and the second row decoder RD2 may respectively select the normal data word line WL_N and the metadata word line WL_M at the same time. In addition, a specific CSL may be selected by the first column decoder CD1 and the second column decoder CD2.
[0062] Then, the word line and CSL can be selected by the row decoders RD1 and RD2 and the column decoders CD1 and CD2, and the data on the selected word line and the selected CSL (not shown) can be read or written by the GIO line connected to each sub-memory bank. For example, the same GIO can be used to Figure 3 The sub-bank included in the first bank B1 shown in FIG. 1 reads data and is used to read data from the sub-bank as shown in FIG. Figure 4 The sub-bank shown in FIG. 8 reads data included in the second bank B2.
[0063] According to the above-described embodiment, a single memory bank may include sub-memory banks divided by a row decoder interposed therebetween, and thus different memory banks may share the same GIO. Therefore, when a normal data word line and a metadata word line are activated at the same time, normal data and metadata may be output at the same time without timing loss. In addition, sub-memory banks of different memory banks may share the same GIO to simultaneously output normal data and metadata without an additional GIO.
[0064] Figure 5 and Figure 6 is a diagram illustrating a word line allocation method according to an example embodiment. As an example, Figure 5 shows the case where the required normal / element ratio is n=8, and Figure 6A case where the required normal / meta ratio is n = 16 is shown. For example, the required ratio of word lines allocated for normal data to word lines allocated for meta data may be n:1. Figure 5 An example is shown which may correspond to a situation where the required normal / meta ratio is 8:1, and Figure 6 An example is shown which may correspond to a situation where the required normal / meta ratio is 16:1.
[0065] Reference Figure 5 and Figure 6 , a single memory bank B may be connected to a plurality of word lines. In an example embodiment, among the plurality of word lines, in the column direction d1, every r-th word line (where r is a positive integer) may be allocated for metadata. For example, the remaining word lines except for every r-th word line may be allocated for normal data. According to an example embodiment, the word lines allocated for metadata are not newly added, but a portion of word lines already present in an existing memory device is allocated for this purpose.
[0066] In an example embodiment, a single memory bank (e.g., a first memory bank B1) may include two sub-memory banks (a first sub-memory bank SB1 and a second sub-memory bank SB2) divided in a row direction d2. The first sub-memory bank SB1 may be connected to a plurality of first word lines WL1-0 to WL1-(32k-1) among a plurality of word lines, and the second sub-memory bank SB2 may be connected to a plurality of second word lines WL2-0 to WL2-(32k-1) among a plurality of word lines. The number of first word lines and second word lines may be 32k (where k is, for example, 1024). In an example embodiment, every r-th word line connected to a sub-memory bank within a single memory bank B may be allocated metadata for another sub-memory bank, and every r-th word line connected to another sub-memory bank may be allocated metadata for one sub-memory bank. In this case, the word line allocated for metadata in one sub-memory bank may correspond to the word line allocated for normal data in another sub-memory bank. For example, among the multiple first word lines WL1-0 to WL1-(32k-1) of the first sub-storage body SB1, in the column direction d1, every r-th first word line can be allocated for metadata of the second sub-storage body SB2, and among the multiple second word lines WL2-0 to WL2-(32k-1) of the second sub-storage body SB2, in the column direction d1, every r-th second word line can be allocated for metadata of the first sub-storage body SB1.
[0067] Allocating a word line connected to one sub-memory bank for metadata of another sub-memory bank may mean allocating a word line for metadata corresponding to normal data to be written or read in another sub-memory bank. Therefore, according to example embodiments, a word line for normal data and a word line for metadata corresponding to normal data may be set to intersect each other in terms of sub-memory banks.
[0068] Then, a ratio of first word lines allocated for metadata to remaining first word lines among the first word lines may be 1:(r-1), and a ratio of second word lines allocated for metadata to remaining second word lines among the second word lines may be 1:(r-1).
[0069] For example, every r-th first word line may be allocated to every 1st second word line WL2-0 to every (r-1)th second word line WL2-(r-2) among the plurality of second word lines WL2-0 to WL2-(32k-1). Every r-th second word line may be allocated to every 1st first word line WL1-0 to every (r-1)th first word line WL1-(r-2) among the plurality of first word lines WL1-0 to WL1-(32k-1). For example, among the multiple first word lines WL1-0 to WL1-(32k-1) of the first sub-storage body SB1, every rth first word line can be allocated to read or write metadata corresponding to normal data of every 1st second word line to every (r-1)th second word line of the second sub-storage body SB2, and among the multiple second word lines WL2-0 to WL2-(32k-1) of the second sub-storage body SB2, every rth second word line can be allocated to read or write metadata corresponding to normal data of every 1st first word line to every (r-1)th first word line.
[0070] For example, when Figure 5 When n is 8, r can be 8. For example, referring to Figure 5 , when the required ratio of word lines allocated for normal data to word lines allocated for metadata is 8:1, every eighth word line may be allocated for metadata. Then, every eighth word line may be allocated for metadata, and every first word line to every seventh word line may be allocated for normal data. Therefore, the ratio of normal data word lines to metadata word lines may be 7:1.
[0071] according to Figure 5, in order to support the situation where the ratio of word lines allocated for normal data to word lines allocated for metadata is 8:1, every eighth word line of one sub-memory bank may be allocated to read or write metadata corresponding to normal data of every first to seventh word lines of another sub-memory bank. For example, the 1-0th word line WL1-0 to the 1-6th word line WL1-6 of the first sub-memory bank SB1 may be allocated for normal data, and the 2-7th word line WL2-7 may be allocated to read and write metadata corresponding to "normal data written into or read from the 1-0th word line WL1-0 to the 1-6th word line WL1-6 of the first sub-memory bank SB1". In contrast, the 2-0 word line WL2-0 to the 2-6 word line WL2-6 of the second sub-storage body SB2 may be allocated for normal data, and the 1-7 word lines WL1-7 of the first sub-storage body SB1 may be allocated to read and write metadata corresponding to “normal data written into or read from the 2-0 word line WL2-0 to the 2-6 word line WL2-6 of the second sub-storage body SB2.” As a result, in the 1-0 word line WL1-0 to the 1-7 word line WL1-7 of the first sub-storage body SB1 (or the 2-0 word line WL2-0 to the 2-7 word line WL2-7 of the second sub-storage body SB2), the ratio of normal data to metadata may be 7:1. The above allocation relationship may be repeated from the last word line in the column direction (eg, the 1st-(32k-1) word line WL1-(32k-1) and the 2nd-(32k-1) word line WL2-(32k-1)).
[0072] Reference Figure 6 , when n is 16, r can be 16. For example, referring to Figure 6 , when the required ratio of word lines allocated for normal data to word lines allocated for metadata is 16:1, every sixteenth word line may be allocated for metadata. Then, every sixteenth word line may be allocated for metadata, and every first word line to every fifteenth word line may be allocated for normal data. Therefore, the ratio of normal data word lines to metadata word lines may be 15:1.
[0073] according to Figure 6, in order to support the situation where the ratio of word lines allocated for normal data to word lines allocated for metadata is 16:1, every sixteenth word line of one sub-memory bank may be allocated to read or write metadata corresponding to normal data of every first word line to every fifteenth word line of another sub-memory bank. For example, the 1-0 word lines WL1-0 to the 1-14 word lines WL1-14 of the first sub-memory bank SB1 may be allocated for normal data, and the 2-15 word lines WL2-15 of the second sub-memory bank SB2 may be allocated to read and write metadata corresponding to "normal data written into or read from the 1-0 word lines WL1-0 to the 1-14 word lines WL1-14 of the first sub-memory bank SB1". In contrast, the 2-0 word line WL2-0 to the 2-14 word line WL2-14 of the second sub-storage body SB2 may be allocated for normal data, and the 1-15 word line WL1-15 of the first sub-storage body SB1 may be allocated to read and write metadata corresponding to “normal data written in or read from the 2-0 word line WL2-0 to the 2-14 word line WL2-14 of the second sub-storage body SB2.” As a result, in the 1-0 word line WL1-0 to the 1-15 word line WL1-15 of the first sub-storage body SB1 (or the 2-0 word line WL2-0 to the 2-15 word line WL2-15 of the second sub-storage body SB2), the ratio of normal data to metadata may be 15:1. The above allocation relationship may be repeated from the last word line in the column direction (eg, the 1st-(32k-1) word line WL1-(32k-1) and the 2nd-(32k-1) word line WL2-(32k-1)).
[0074] According to the above-described embodiment, a portion of the existing word lines can be allocated for metadata to significantly meet the required normal / meta ratio without adding new lines. For example, the allocation relationship between the normal data word lines and the metadata word lines can be constructed to intersect between sub-memory banks, so that normal data and metadata can be output at the same time.
[0075] In this case, by Figure 5 and Figure 6The example embodiment of the present invention shows that a single memory bank (e.g., first memory bank B1) divided into a first sub-memory bank SB1 and a second sub-memory bank SB2 can be operated in the same functional manner as a memory bank that is not divided into sub-memory banks. For example, the first sub-memory bank SB1 is internally connected to a plurality of first word lines WL1-0 to WL1-(32k-1), and the second sub-memory bank SB2 is internally connected to a plurality of second word lines WL2-0 to WL2-(32k-1), which can be operated in the same manner as a single memory bank connected to a total of 64k word lines (e.g., WL0 to WL(64k-1)). For example, the plurality of first word lines WL1-0 to WL1-(32k-1) and the plurality of second word lines WL2-0 to WL2-(32k-1) may correspond to the first word line WL0 to the 32kth word line WL(32k-1) and the 32k+1th word line WL32k to the 64kth word line WL(64k-1) among the total 64k word lines (e.g., WL0 to WL(64k-1)), respectively. Figure 5 In an example embodiment, a first sub-storage body SB1 connected to a plurality of first word lines WL1-0 to WL1-(32k-1) and a second sub-storage body SB2 connected to a plurality of second word lines WL2-0 to WL2-(32k-1) may correspond to a portion connected to the first 32k word lines (e.g., WL0 to WL(32k-1)) and a portion connected to the last 32k word lines (e.g., WL32k to WL(64k-1)) in a storage body without a sub-storage body structure, respectively.
[0076] according to Figure 5 and Figure 6 The number of word lines of the above-mentioned example embodiments is only an example, and can be set in various ways according to the memory capacity. For example, when the number of rows that can be selected by each of the first row decoder RD1 and the second row decoder RD2 according to the above-mentioned example embodiments is N (wherein N is a positive integer), the first sub-storage body SB1 can be connected to N first word lines, and the second sub-storage body SB2 can be connected to N second word lines. Therefore, the first sub-storage body SB1 and the second sub-storage body SB2 can be operated in the same manner as a single storage body connected to a total of 2N word lines. In the following, for ease of description, an example in which the number of word lines in each sub-storage body is 32k will be provided.
[0077] Figure 7 is a diagram illustrating a sub-bank according to example embodiments.
[0078] Reference Figure 7 , the sub-storage bank SB according to the example embodiment may correspond to the above Figures 2 to 6One of the sub-storage bodies SB included in the single storage body described in , and can be connected to a plurality of word lines WL0 to WL(32k-1) extending in the row direction d2, a plurality of CSL subsets L_CS0 to U_CS(i-1) extending in the column direction d1, a row decoder RD, and a column decoder CD. The sub-storage body SB may include a plurality of matrices MAT. Some word lines and some CSLs may be connected to each of the matrices MAT. The MAT may include an array of memory cells arranged in two dimensions, and each memory cell may be connected to: a single word line among some word lines connected to the corresponding MAT and a single CSL among some CSLs.
[0079] In one example embodiment, the column decoder CD connected to each sub-storage body SB may include a plurality of CSL blocks CB and a single error correction code (ECC) block. Each of the CSL block CB and the ECC block may be configured to select the CSL based on a column address decoded from the column decoder CD. The CSL block CB and the ECC block may be arranged in a row direction d2 corresponding to the CSL. For example, among a plurality of MATs, the MAT connected to the column corresponding to the ECC block may store a parity bit generated from the ECC block.
[0080] In one example embodiment, the ECC block may be arranged to correspond to a middle column among a plurality of columns formed by a plurality of MATs included in the sub-storage body SB. For example, for a single sub-storage body SB, a plurality of CSL blocks CB may be arranged symmetrically with respect to the ECC block. Therefore, the CSLs connected to the plurality of CSL blocks CB may also be arranged symmetrically with respect to the CSLs connected to the ECC block.
[0081] A plurality of CSL subsets L_CS0 to U_CS(i-1) may be connected to a plurality of MATs corresponding to a single CSL block CB. As shown in the figure, a pair of CSL subsets may be selected from among the plurality of CSL subsets L_CS0 to U_CS(i-1) during a single access. For example, on a first side L relative to an ECC block, a pair of CSL subsets L_CS0 and L_CS1 to a pair of CSL subsets L_CS(i-2) and L_CS(i-1) (where i is a positive integer) may be selected, and on a second side U relative to the ECC block, a pair of CSL subsets U_CS0 and U_CS1 to a pair of CSL subsets U_CS(i-2) and U_CS(i-1) may be selected. In addition, a pair of CSL subsets M_CS0 and M_CS1 may be selected in the ECC block.
[0082] Figure 8 It is shown Figure 7 FIG. 1 is a diagram of an example of area “A”.
[0083] Reference Figure 8, for example, a plurality of CSLs that may be classified as CSL groups CS1 and CS2 may be connected to a plurality of MATs corresponding to a single CSL block CB. A portion of the plurality of CSLs may be connected to each of the CSL groups CS1 and CS2. As an example, a plurality of CSLs (for example, 64 CSLs CSL0 to CSL63 as shown) may be connected to each of the CSL groups CS1 and CS2. Therefore, a total of 128 CSLs may be connected to a single CSL block CB. During a single access, a single CSL may be selected from each of the CSL groups CS1 and CS2. Hereinafter, unless otherwise specified, the CSLs selected from the CSL groups CS1 and CS2 of each CSL block CB and ECC block in a single sub-storage body SB will be referred to as CSL subsets, and the CSLs selected for each CSL block CB will be referred to as a pair of CSL subsets.
[0084] Return to Figure 7 , a pair of CSL subsets corresponding to a single CSL block CB included in a single sub-memory bank SB or a portion of the pair of CSL subsets may be allocated to a single word line (e.g., a single word line among word lines for normal data) connected to the remaining sub-memory banks that constitute a memory bank together with the single sub-memory bank SB. For example, all CSL subsets included in the single sub-memory bank SB may each be allocated to one of the normal data word lines connected to the remaining sub-memory banks. According to example embodiments, referring to Figure 6 , a single sub-storage bank SB may correspond to Figure 6 The first sub-memory bank SB1, the remaining sub-memory banks may correspond to Figure 6 The second sub-memory body SB2.
[0085] For example, a single memory bank may include one sub-memory bank SB and another sub-memory bank. In this case, when access to normal data is performed through the remaining word lines except every r-th word line in one sub-memory bank SB, access to metadata may be performed on every r-th word line in another sub-memory bank. In this case, a pair of CSL subsets or a portion of the pair of CSL subsets in another sub-memory bank may be allocated to each remaining word line of a single sub-memory bank SB. Therefore, when access to normal data is performed on one of the remaining word lines of a single sub-memory bank SB, access to metadata may be performed on the pair of CSL subsets or a portion of the pair of CSL subsets allocated to one of the remaining word lines.
[0086] All CSL subsets may be selected in the normal-side sub-bank SB where access to normal data is performed. Therefore, access to normal data may be performed on a normal data word line and all CSL subsets.
[0087] In an example embodiment, among the CSL subsets connected to a single sub-storage body SB, a pair of CSL subsets L_CS0 and L_CS1 to L_CS(i-2) and L_CS(i-1) included in a first side L, and a pair of CSL subsets U_CS0 and U_CS1 to U_CS(i-2) and U_CS(i-1) included in a second side U can be sequentially assigned to normal data word lines connected to the remaining sub-storage bodies SB from a pair of CSL subsets having the lowest index.
[0088] In an example embodiment, among the CSL subsets connected to a single sub-storage body SB, the CSL subsets L_CS0 to L_CS(i-1) included in the first side L and the CSL subsets U_CS0 to U_CS(i-1) included in the second side U can be sequentially assigned to the normal data word lines connected to the remaining sub-storage bodies SB from the CSL subset with the lowest index.
[0089] Fig. 9 and Fig.10 is a diagram illustrating column selection signals of normal data and metadata according to various embodiments. Fig. 9 and Fig.10 An example implementation of a combination of meta-side subbank (MSB) side column selection signals corresponding to normal-side subbank (NSB) side column selection signals is shown. Although the distinction between NSB and MSB is based on where normal data is stored, each subbank can be considered to be based on the NSB and MSB of the relative subbank. For example, referring to Figure 6 , when the first sub-memory bank SB1 is NSB, the MSB may be the second sub-memory bank SB2. Also, when SB2 is NSB, the MSB may be the first sub-memory bank SB1.
[0090] exist Fig. 9 and Fig.10 In the embodiment, CSLx[m:n] may be defined as a column selection signal (a signal for selecting CSL). The column selection signal may be generated by a column decoder.
[0091] Here, m and n represent the range of CSL subsets to be selected from multiple CSL subsets assigned to a single storage body (or sub-storage body), and m and n are also positive integers. For example, m represents the lowest index among the indexes of the CSL subsets to be selected, and n represents the highest index among the indexes of the CSL subsets to be selected.
[0092] The column decoder may select an mth CSL subset to an nth CSL subset from the CSL subsets for each of the first side and the second side of a single memory bank (or sub-memory bank) based on CSLx[m:n], and may select an xth CSL from a plurality of CSLs corresponding to the selected CSL subset. Figure 7 When m=0 and n=1 in , the column decoder may select L_CS0 and L_CS1 on the first side L, and select U_CS0 and U_CS1 on the second side U.
[0093] Here, x means to Figure 8 The index of the CSL selected from the plurality of CSLs included in each pair of CSL subsets in , and x is a positive integer. Figure 8 , for example, when x=1, CSL1 may be selected from CS1, and CSL1 may be selected from CS2.
[0094] Return to Fig. 9 For example, when the required normal / meta ratio is 8, according to an example embodiment, every eighth word line may be allocated for metadata. For example, the ratio of word lines allocated for normal data to word lines allocated for metadata may actually be 7:1 (e.g., normal 8(7), meta 1). This is intended to significantly meet the required 8:1 ratio without additional chip size overhead.
[0095] As for the normal side sub-memory bank NSB, access to normal data may be performed on each of the first to seventh word lines WL0 to WL6. In this case, the column selection signal for the normal side sub-memory bank NSB may be CSLx[0:15] to select all CSL subsets, and the value of x may be as follows: Fig. 9 The range shown in φL7 is from 0 to 63. The eighth word line WL7 of the normal-side sub-memory bank NSB may be allocated for the meta-side sub-memory bank MSB.
[0096] Next, with respect to the meta-side sub-memory bank MSB, the eighth word line WL7 may be allocated for the normal-side sub-memory bank NSB. In this case, the column selection signal may be defined based on the word line accessed in the normal-side sub-memory bank NSB. For example, according to the above-described embodiment, a pair of CSL subsets of the meta-side sub-memory bank MSB may be sequentially allocated to the normal data word lines connected to the normal-side sub-memory bank NSB. For example, when the first word line WL0 of the normal-side sub-memory bank NSB is accessed, the m and n of the column selection signal may be determined as 0 and 1, respectively, to select a pair of CSL subsets with the lowest index. Next, when the second word line WL1 of the normal-side sub-memory bank NSB is accessed, the m and n of the column selection signal may be determined as 2 and 3, respectively, to select a pair of CSL subsets with the next index. When the last seventh word line WL6 is accessed, the m and n of the column selection signal may be determined as 12 and 13, respectively, based on the above-described allocation relationship. According to the above-described embodiment, the fifteenth CSL subset and the sixteenth CSL subset on the meta side may not be allocated.
[0097] According to the above Fig. 9 , for example, when each CSL is connected to eight bit lines, during access to a single word line, 256 bits of normal data (8 bits × 32 (the number of CSL subsets selected in the normal-side sub-storage bank NSB)), 32 bits of metadata (8 bits × 4 (the number of CSL subsets selected in the meta-side sub-storage bank MSB)) and 16 bits of parity bits can be output.
[0098] Reference Fig.10 For example, when the required normal / meta ratio is 16, according to an example embodiment, every sixteenth word line may be allocated for metadata. For example, the ratio of word lines allocated for normal data to word lines allocated for metadata may actually be 15:1 (e.g., normal 16 (15), meta 1). This is intended to significantly meet the required 16:1 ratio without additional chip size overhead.
[0099] As for the normal side sub-memory bank NSB, access to normal data may be performed on each of the first word line WL0 to the fifteenth word line WL14. As described above, the column selection signal of the normal side sub-memory bank NSB may be CSLx[0:15] to select all CSL subsets. Similarly, the sixteenth word line WL15 of the normal side sub-memory bank NSB may be allocated for the meta side sub-memory bank MSB.
[0100] Next, with respect to the meta-side sub-memory bank MSB, the sixteenth word line WL15 may be allocated for the normal-side sub-memory bank NSB. For example, according to the above-described embodiment, the CSL subsets of the meta-side sub-memory bank MSB may be sequentially allocated from the CSL subset with the lowest index to the normal data word lines for normal data connected to the normal-side sub-memory bank NSB. Fig. 9 Differently, only one CSL subset is selected so that the column select signal of the meta-side sub-bank MSB may be defined as CSLx[m].
[0101] For example, when the first word line WL0 of the normal-side sub-memory bank NSB is accessed, the m of the column selection signal may be determined to be 0 to select the CSL subset with the lowest index. Next, when the second word line WL1 of the normal-side sub-memory bank NSB is accessed, the m of the column selection signal may be determined to be 1 to select the CSL subset with the next index. According to the above allocation relationship, when the last fifteenth word line WL14 is accessed, the m of the column selection signal may be determined to be 14. According to the above embodiment, the sixteenth CSL subset on the element side may not be allocated.
[0102] According to the above Fig.10 , for example, when each CSL is connected to eight bit lines, during access to a single word line, 256 bits of normal data (8 bits × 32 (the number of CSL subsets selected in the normal-side sub-storage bank NSB)), 16 bits of metadata (8 bits × 2 (the number of CSL subsets selected in the meta-side sub-storage bank MSB)) and 16 bits of parity bits can be output.
[0103] In the following, Figures 11 to 34 In Figures 7 to 10 The example embodiments shown in FIG. 1 are used to describe various embodiments of the allocation relationship between word lines and CSLs. Unless otherwise specified, the symbol “L” representing a CSL subset may be defined as representing Figure 7 The first side L, and "U" can be defined as representing Figure 7 The second side U. Figures 11 to 22 An example implementation is shown when the required normal / meta ratio is 8 (eg, when r=8), Figures 23 to 34 An example implementation is shown when the required normal / meta ratio is 16 (eg, when r=16).
[0104] Fig.11 and Fig.12 is a diagram showing an allocation relationship between a first word line and a CSL when the first sub bank SB1 is a normal-side sub bank.
[0105] Reference Fig.11 , the first sub-storage bank SB1 may include a plurality of MATs and may be connected to a plurality of first CSL subsets L_CS1-0 to U_CS1-15. Fig.12, the second sub-storage body SB2 may include a plurality of MATs and may be connected to a plurality of second CSL subsets L_CS2-0 to U_CS2-15. In this case, among the first CSL subsets L_CS1-0 to U_CS1-15, the ECC CSL subsets M_CS1-0 and M_CS1-1 may be connected to the ECC block of the first sub-storage body SB1, and the first side CSL subset and the second side CSL subset L_CS1-0 to U_CS1-15 may be connected to each CSL block CB. In addition, among the second CSL subsets L_CS2-0 to U_CS2-15, the ECC CSL subsets M_CS2-0 and M_CS2-1 may be connected to the ECC block of the second sub-storage body SB2, and the first side CSL subset and the second side CSL subset L_CS2-0 to U_CS2-15 may be connected to each CSL block CB. The plurality of CSLs may be selected based on the column selection signal Figure 8 Each of the CSL blocks CB respectively selects a plurality of first CSL subsets L_CS1-0 to U_CS1-15 and a plurality of second CSL subsets L_CS2-0 to U_CS2-15.
[0106] According to an example embodiment, every r-th word line of the first sub-memory bank SB1 and the second sub-memory bank SB2 may be allocated for metadata. For example, when r=8, the 1st first word line WL1-0 may be selected by the first row decoder RD1 connected to the first sub-memory bank SB1 to read or write normal data. In this case, the 8th second word line WL2-7 may be selected by the second row decoder RD2 connected to the second sub-memory bank SB2 to read or write metadata corresponding to normal data.
[0107] Furthermore, among the second CSL subsets L_CS2 - 0 to U_CS2 - 15 , a pair of first side CSL subsets L_CS2 - 0 and L_CS2 - 1 and a pair of second side CSL subsets U_CS2 - 0 and U_CS2 - 1 may be allocated to the 1 st first word line WL1 - 0 .
[0108] Then, the first column decoder CD1 may select all CSL subsets L_CS1-0 to U_CS1-15 for the first sub-memory bank SB1 as the normal-side sub-memory bank, and the second column decoder CD2 may select a pair of first-side CSL subsets L_CS2-0 and L_CS2-1 and a pair of second-side CSL subsets U_CS2-0 and U_CS2-1 allocated for metadata for the second sub-memory bank SB2 as the meta-side sub-memory bank. In this case, the column selection signal for selecting the CSL subset may be CSLx[0:15] (where x is one of 0 to 63) generated from the first column decoder CD1, and the column selection signal for selecting the CSL subset may be CSLx[0:1] (where x is one of 0 to 63) generated from the second column decoder CD2.
[0109] Therefore, from the first sub-memory bank SB1 as the normal-side sub-memory bank, normal data can be output from the 1st first word line WL1-0 and multiple CSL subsets L_CS1-0 to U_CS1-15. In addition, from the second sub-memory bank SB2 as the meta-side sub-memory bank, meta data corresponding to the normal data can be output simultaneously from the 8th second word line WL2-7, a pair of first-side CSL subsets L_CS2-0 and L_CS2-1, and a pair of second-side CSL subsets U_CS2-0 and U_CS2-1.
[0110] Fig.13 and Fig.14 is a diagram showing an allocation relationship between a second word line and a CSL when the first sub bank SB1 is a normal-side sub bank.
[0111] Reference Fig.13 and Fig.14 When the 2nd first word line WL1-1 is selected by the first row decoder RD1 connected to the first sub-storage body SB1 to read or write normal data, the 8th second word line WL2-7 can also be selected by the second row decoder RD2 connected to the second sub-storage body SB2 to read or write metadata corresponding to the normal data.
[0112] Among the second CSL subsets L_CS2-0 to U_CS2-15, a pair of first side CSL subsets L_CS2-2 and L_CS2-3 and a pair of second side CSL subsets U_CS2-2 and U_CS2-3 may be allocated to the 2nd first word line WL1-1.
[0113] Then, the first column decoder CD1 may select all CSL subsets L_CS1-0 to U_CS1-15 for the first sub-storage bank SB1 as the normal-side sub-storage bank, and the second column decoder CD2 may select a pair of first-side CSL subsets L_CS2-2 and L_CS2-3 and a pair of second-side CSL subsets U_CS2-2 and U_CS2-3 allocated for metadata for the second sub-storage bank SB2 as the meta-side sub-storage bank. In this case, the column selection signal for selecting the CSL subset may be CSLx[0:15] (where x is one of 0 to 63) generated from the first column decoder CD1, and the column selection signal for selecting the CSL subset may be CSLx[2:3] (where x is one of 0 to 63) generated from the second column decoder CD2.
[0114] Therefore, from the first sub-memory bank SB1 as the normal-side sub-memory bank, normal data can be output from the 2nd first word line WL1-1 and a plurality of first CSL subsets L_CS1-0 to U_CS1-15. In addition, from the second sub-memory bank SB2 as the meta-side sub-memory bank, meta data corresponding to the normal data can be output simultaneously from the 8th second word line WL2-7, a pair of first-side CSL subsets L_CS2-2 and L_CS2-3, and a pair of second-side CSL subsets U_CS2-2 and U_CS2-3.
[0115] Each pair of CSL subsets of the second sub-bank SB2 may be sequentially allocated from the 3rd first word line to the last word line of the first sub-bank SB1.
[0116] Fig.15 and Fig.16 is a diagram illustrating an allocation relationship between a last word line and a CSL when a first sub bank SB1 is a normal-side sub bank according to an embodiment.
[0117] Reference Fig.15 and Fig.16 , when the 7th first word line WL1-6 is selected by the first row decoder RD1 connected to the first sub-storage body SB1 to read or write normal data, the 8th second word line WL2-7 can also be selected by the second row decoder RD2 connected to the second sub-storage body SB2 to read or write metadata corresponding to the normal data.
[0118] The first column decoder CD1 may select all CSL subsets L_CS1-0 to U_CS1-15 for the first sub-storage bank SB1 as the normal-side sub-storage bank, and the second column decoder CD2 may select a pair of first-side CSL subsets L_CS2-12 and L_CS2-13 and a pair of second-side CSL subsets U_CS2-12 and U_CS2-13 allocated for metadata for the second sub-storage bank SB2 as the meta-side sub-storage bank. In this case, the column selection signal for selecting the CSL subset may be CSLx[0:15] (where x is one of 0 to 63) generated from the first column decoder CD1, and the column selection signal for selecting the CSL subset may be CSLx[12:13] (where x is one of 0 to 63) generated from the second column decoder CD2.
[0119] Therefore, from the first sub-memory bank SB1 as the normal-side sub-memory bank, normal data can be output from the 7th first word line WL1-6 and a plurality of first CSL subsets L_CS1-0 to U_CS1-15. In addition, from the second sub-memory bank SB2 as the meta-side sub-memory bank, meta data corresponding to the normal data can be output simultaneously from the 8th second word line WL2-7, a pair of first-side CSL subsets L_CS2-12 and L_CS2-13, and a pair of second-side CSL subsets U_CS2-12 and U_CS2-13.
[0120] In this case, a pair of CSL subsets L_CS2-14 and L_CS2-15, and U_CS2-14 and U_CS2-15 corresponding to CSLx[14:15] in the second sub-bank SB2 may not be allocated to the word lines of the first sub-bank SB1.
[0121] Fig.17 and Fig.18 is a diagram showing an allocation relationship between the first word line and the CSL when the second sub bank SB2 is a normal-side sub bank.
[0122] Reference Fig.17 and Fig.18 , when the 1st second word line WL2-0 is selected by the second row decoder RD2 connected to the second sub-memory bank SB2 to read or write normal data, the 8th first word line WL1-7 can be selected by the first row decoder RD1 connected to the first sub-memory bank SB1 to read or write metadata corresponding to the normal data. For example, Fig.17 and Fig.18 The distribution relationship can be Fig.11 and Fig.12 The allocation relationship has a cross structure.
[0123] The second column decoder CD2 may select all CSL subsets L_CS2-0 to U_CS2-15 for the second sub-storage bank SB2 as the normal-side sub-storage bank, and the first column decoder CD1 may select a pair of first-side CSL subsets L_CS1-0 and L_CS1-1 and a pair of second-side CSL subsets U_CS1-0 and U_CS1-1 allocated for metadata for the first sub-storage bank SB1 as the meta-side sub-storage bank. In this case, the column selection signal for selecting the CSL subset may be CSLx[0:15] (where x is one of 0 to 63) generated from the second column decoder CD2, and the column selection signal for selecting the CSL subset may be CSLx[0:1] (where x is one of 0 to 63) generated from the first column decoder CD1.
[0124] Therefore, from the second sub-memory bank SB2 as the normal-side sub-memory bank, normal data can be output from the 1st second word line WL2-0 and a plurality of second CSL subsets L_CS2-0 to U_CS2-15. In addition, from the first sub-memory bank SB1 as the meta-side sub-memory bank, meta data corresponding to the normal data can be output simultaneously from the 8th first word line WL1-7, a pair of first-side CSL subsets L_CS1-0 and L_CS1-1, and a pair of second-side CSL subsets U_CS1-0 and U_CS1-1.
[0125] Fig.19 and Fig. 20 2 is a diagram showing an allocation relationship between a second word line and a CSL when the second sub bank SB2 is a normal-side sub bank.
[0126] Reference Fig.19 and Fig. 20 , when the 2nd second word line WL2-1 is selected by the second row decoder RD2 connected to the second sub-memory bank SB2 to read or write normal data, the 8th first word line WL1-7 can be selected by the first row decoder RD1 connected to the first sub-memory bank SB1 to read or write metadata corresponding to the normal data. For example, Fig.19 and Fig. 20 The distribution relationship can be Fig.13 and Fig.14 The distribution relationship has a cross structure.
[0127] The second column decoder CD2 may select all CSL subsets L_CS2-0 to U_CS2-15 for the second sub-storage bank SB2 as the normal-side sub-storage bank, and the first column decoder CD1 may select a pair of first-side CSL subsets L_CS1-2 and L_CS1-3 and a pair of second-side CSL subsets U_CS1-2 and U_CS1-3 allocated for metadata for the first sub-storage bank SB1 as the meta-side sub-storage bank. In this case, the column selection signal for selecting the CSL subset may be CSLx[0:15] (where x is one of 0 to 63) generated from the second column decoder CD2, and the column selection signal for selecting the CSL subset may be CSLx[2:3] (where x is one of 0 to 63) generated from the first column decoder CD1.
[0128] Each pair of CSL subsets of the first sub-bank SB1 may be sequentially allocated from the 3rd second word line to the last word line of the second sub-bank SB2.
[0129] Fig.21 and Fig. 22 is a diagram showing an assignment relationship between the last word line and the CSL when the second sub bank SB2 is a normal-side sub bank.
[0130] Reference Fig.21 and Fig. 22 , when the 7th second word line WL2-6 is selected by the second row decoder RD2 connected to the second sub-memory bank SB2 to read or write normal data, the 8th first word line WL1-7 can be selected by the first row decoder RD1 connected to the first sub-memory bank SB1 to read or write metadata corresponding to the normal data. For example, Fig.21 and Fig. 22 The distribution relationship can be Fig.15 and Fig.16 The distribution relationship has a cross structure.
[0131] The second column decoder CD2 may select all CSL subsets L_CS2-0 to U_CS2-15 for the second sub-storage bank SB2 as the normal-side sub-storage bank, and the first column decoder CD1 may select a pair of first-side CSL subsets L_CS1-12 and L_CS1-13 and a pair of second-side CSL subsets U_CS1-12 and U_CS1-13 allocated for metadata for the first sub-storage bank SB1 as the meta-side sub-storage bank. In this case, the column selection signal for selecting the CSL subset may be CSLx[0:15] (where x is one of 0 to 63) generated from the second column decoder CD2, and the column selection signal for selecting the CSL subset may be CSLx[12:13] (where x is one of 0 to 63) generated from the first column decoder CD1.
[0132] A pair of CSL subsets L_CS1-14 and L_CS1-15, and U_CS1-14 and U_CS1-15 corresponding to CSLx[14:15] in the first sub-bank SB1 may not be allocated to word lines of the second sub-bank SB2.
[0133] Fig.23 and Fig.24 is a diagram showing an allocation relationship between a first word line and a CSL when the first sub bank SB1 is a normal-side sub bank.
[0134] Reference Fig.23 and Fig.24 According to an example embodiment, every r-th word line of the first sub-memory bank SB1 and the second sub-memory bank SB2 may be allocated for metadata (for example, r may be 16). When the 1st first word line WL1-0 is selected by the first row decoder RD1 connected to the first sub-memory bank SB1 to read or write normal data, the 16th second word line WL2-15 may be selected by the second row decoder RD2 connected to the second sub-memory bank SB2 to read or write metadata corresponding to the normal data.
[0135] Among the second CSL subsets L_CS2 - 0 to U_CS2 - 15 , the first side CSL subset L_CS2 - 0 and the second side CSL subset U_CS2 - 0 may be allocated to the 1 st first word line WL1 - 0 .
[0136] Then, the first column decoder CD1 may select all CSL subsets L_CS1-0 to U_CS1-15 for the first sub-storage bank SB1 as the normal-side sub-storage bank, and the second column decoder CD2 may select the first-side CSL subset L_CS2-0 and the second-side CSL subset U_CS2-0 allocated for metadata for the second sub-storage bank SB2 as the meta-side sub-storage bank. In this case, the column selection signal for selecting the CSL subset may be CSLx[0:15] (where x is one of 0 to 63) generated from the first column decoder CD1, and the column selection signal for selecting the CSL subset may be CSLx[0] (where x is one of 0 to 63) generated from the second column decoder CD2.
[0137] Therefore, from the first sub-memory bank SB1 as the normal-side sub-memory bank, normal data can be output from the 1st first word line WL1-0 and multiple first CSL subsets L_CS1-0 to U_CS1-15. In addition, from the second sub-memory bank SB2 as the meta-side sub-memory bank, meta data corresponding to the normal data can be output simultaneously from the 16th second word line WL2-15, the single first-side CSL subset L_CS2-0 and the single second-side CSL subset U_CS2-0.
[0138] Fig.25and Fig.26 is a diagram showing an allocation relationship between a second word line and a CSL when the first sub bank SB1 is a normal-side sub bank.
[0139] Reference Fig.25 and Fig.26 When the 2nd first word line WL1-1 is selected by the first row decoder RD1 connected to the first sub-storage body SB1 to read or write normal data, the 16th second word line WL2-15 can also be selected by the second row decoder RD2 connected to the second sub-storage body SB2 to read or write metadata corresponding to the normal data.
[0140] Among the second CSL subsets L_CS2 - 0 to U_CS2 - 15 , the first side CSL subset L_CS2 - 1 and the second side CSL subset U_CS2 - 1 may be allocated to the 2 nd first word line WL1 - 1 .
[0141] Then, the first column decoder CD1 may select all CSL subsets L_CS1-0 to U_CS1-15 for the first sub-storage bank SB1 as the normal-side sub-storage bank, and the second column decoder CD2 may select the first-side CSL subset L_CS2-1 and the second-side CSL subset U_CS2-1 allocated for metadata for the second sub-storage bank SB2 as the meta-side sub-storage bank. In this case, the column selection signal for selecting the CSL subset may be CSLx[0:15] (where x is one of 0 to 63) generated from the first column decoder CD1, and the column selection signal for selecting the CSL subset may be CSLx[1] (where x is one of 0 to 63) generated from the second column decoder CD2.
[0142] Therefore, from the first sub-memory bank SB1 as the normal-side sub-memory bank, normal data can be output from the 2nd first word line WL1-1 and multiple first CSL subsets L_CS1-0 to U_CS1-15. In addition, from the second sub-memory bank SB2 as the meta-side sub-memory bank, meta data corresponding to the normal data can be simultaneously output from the 16th second word line WL2-15, the first-side CSL subset L_CS2-1 and the second-side CSL subset U_CS2-1.
[0143] Each CSL subset of the second sub-bank SB2 may be sequentially allocated from the 3rd first word line to the last word line of the first sub-bank SB1.
[0144] Fig. 27 and Fig.28 is a diagram showing an assignment relationship between the last word line and the CSL when the first sub bank SB1 is a normal-side sub bank.
[0145] Reference Fig. 27 and Fig.28When the 15th first word line WL1-14 is selected by the first row decoder RD1 connected to the first sub-storage body SB1 to read or write normal data, the 16th second word line WL2-15 can also be selected by the second row decoder RD2 connected to the second sub-storage body SB2 to read or write metadata corresponding to the normal data.
[0146] The first column decoder CD1 may select all CSL subsets L_CS1-0 to U_CS1-15 for the first sub-storage bank SB1 as a normal-side sub-storage bank, and the second column decoder CD2 may select the first-side CSL subset L_CS2-14 and the second-side CSL subset U_CS2-14 allocated for metadata for the second sub-storage bank SB2 as a meta-side sub-storage bank. In this case, the column selection signal for selecting the CSL subset may be CSLx[0:15] (where x is one of 0 to 63) generated from the first column decoder CD1, and the column selection signal for selecting the CSL subset may be CSLx
[14] (where x is one of 0 to 63) generated from the second column decoder CD2.
[0147] Therefore, from the first sub-memory bank SB1 as the normal-side sub-memory bank, normal data can be output from the 15th first word line WL1-14 and the plurality of first CSL subsets L_CS1-0 to U_CS1-15. In addition, from the second sub-memory bank SB2 as the meta-side sub-memory bank, meta data corresponding to the normal data can be output simultaneously from the 16th second word line WL2-15, the first-side CSL subset L_CS2-14, and the second-side CSL subset U_CS2-14.
[0148] In this case, the CSL subsets L_CS2-15 and U_CS2-15 corresponding to CSLx
[15] in the second sub-bank SB2 may not be allocated to the word lines of the first sub-bank SB1.
[0149] Fig.29 and Fig.30 is a diagram showing an allocation relationship between the first word line and the CSL when the second sub bank SB2 is a normal-side sub bank.
[0150] Reference Fig.29 and Fig.30 , when the 1st second word line WL2-0 is selected by the second row decoder RD2 connected to the second sub-memory bank SB2 to read or write normal data, the 16th first word line WL1-15 can be selected by the first row decoder RD1 connected to the first sub-memory bank SB1 to read or write metadata corresponding to the normal data. For example, Fig.29 and Fig.30 The distribution relationship can be Fig.23 and Fig.24The distribution relationship has a cross structure.
[0151] The second column decoder CD2 may select all CSL subsets L_CS2-0 to U_CS2-15 for the second sub-storage bank SB2 as the normal-side sub-storage bank, and the first column decoder CD1 may select the first-side CSL subset L_CS1-0 and the second-side CSL subset U_CS1-0 allocated for metadata for the first sub-storage bank SB1 as the meta-side sub-storage bank. In this case, the column selection signal for selecting the CSL subset may be CSLx[0:15] (where x is one of 0 to 63) generated from the second column decoder CD2, and the column selection signal for selecting the CSL subset may be CSLx[0] (where x is one of 0 to 63) generated from the first column decoder CD1.
[0152] Therefore, from the second sub-memory bank SB2 as the normal-side sub-memory bank, normal data can be output from the 1st second word line WL2-0 and multiple second CSL subsets L_CS2-0 to U_CS2-15. In addition, from the first sub-memory bank SB1 as the meta-side sub-memory bank, meta data corresponding to the normal data can be output simultaneously from the 8th first word line WL1-7, the first-side CSL subset L_CS1-0 and the second-side CSL subset U_CS1-0.
[0153] Fig.31 and Fig.32 2 is a diagram showing an allocation relationship between a second word line and a CSL when the second sub bank SB2 is a normal-side sub bank.
[0154] Reference Fig.31 and Fig.32 , when the 2nd second word line WL2-1 is selected by the second row decoder RD2 connected to the second sub-memory bank SB2 to read or write normal data, the 16th first word line WL1-15 can be selected by the first row decoder RD1 connected to the first sub-memory bank SB1 to read or write metadata corresponding to the normal data. For example, Fig.31 and Fig.32 The distribution relationship can be Fig.25 and Fig.26 The distribution relationship has a cross structure.
[0155] The second column decoder CD2 may select all CSL subsets L_CS2-0 to U_CS2-15 for the second sub-storage bank SB2 as the normal-side sub-storage bank, and the first column decoder CD1 may select the first-side CSL subset L_CS1-1 and the second-side CSL subset U_CS1-1 allocated for metadata for the first sub-storage bank SB1 as the meta-side sub-storage bank. In this case, the column selection signal for selecting the CSL subset may be CSLx[0:15] (where x is one of 0 to 63) generated from the second column decoder CD2, and the column selection signal for selecting the CSL subset may be CSLx[1] (where x is one of 0 to 63) generated from the first column decoder CD1.
[0156] Each CSL subset of the first sub-bank SB1 may be sequentially allocated from the 3rd second word line to the last word line of the second sub-bank SB2.
[0157] Fig.33 and Fig.34 is a diagram showing an assignment relationship between the last word line and the CSL when the second sub bank SB2 is a normal-side sub bank.
[0158] Reference Fig.33 and Fig.34 , when the 15th second word line WL2-14 is selected by the second row decoder RD2 connected to the second sub-memory bank SB2 to read or write normal data, the 16th first word line WL1-15 can be selected by the first row decoder RD1 connected to the first sub-memory bank SB1 to read or write metadata corresponding to the normal data. For example, Fig.33 and Fig.34 The distribution relationship can be Fig. 27 and Fig.28 The distribution relationship has a cross structure.
[0159] The second column decoder CD2 may select all CSL subsets L_CS2-0 to U_CS2-15 for the second sub-storage bank SB2 as the normal-side sub-storage bank, and the first column decoder CD1 may select the first-side CSL subset L_CS1-14 and the second-side CSL subset U_CS1-14 allocated for metadata for the first sub-storage bank SB1 as the meta-side sub-storage bank. In this case, the column selection signal for selecting the CSL subset may be CSLx[0:15] (where x is one of 0 to 63) generated from the second column decoder CD2, and the column selection signal for selecting the CSL subset may be CSLx
[14] (where x is one of 0 to 63) generated from the first column decoder CD1.
[0160] The CSL subsets L_CS1-15 and U_CS1-15 corresponding to CSLx
[15] in the first sub-bank SB1 may not be allocated to word lines of the second sub-bank SB2.
[0161] According to the above-mentioned embodiment, at least a portion of the multiple first CSL subsets L_CS1-0 to U_CS1-15 may be allocated to one of the remaining second word lines among the multiple second word lines except every r-th second word line, and at least a portion of the multiple second CSL subsets L_CS2-0 to U_CS2-15 may be allocated to one of the remaining first word lines among the multiple first word lines except every r-th first word line.
[0162] According to an example embodiment, when r is 8, at least a portion of the plurality of first CSL subsets L_CS1-0 to U_CS1-15 may be a pair of the first CSL subsets L_CS1-0 to U_CS1-15, and at least a portion of the plurality of second CSL subsets L_CS2-0 to U_CS2-15 may be a pair of the second CSL subsets L_CS2-0 to U_CS2-15.
[0163] Alternatively, according to example embodiments, when r is 16, at least a portion of the plurality of first CSL subsets L_CS1-0 to U_CS1-15 may be a single first CSL subset, and at least a portion of the plurality of second CSL subsets L_CS2-0 to U_CS2-15 may be a single second CSL subset.
[0164] The first row decoder RD1 connected to the first sub-memory body SB1 may be configured to select one of the plurality of first word lines, and the first column decoder CD1 may be configured to select a first CSL subset L_CS1-0 to U_CS1-15 among the plurality of CSLs. In addition, the second row decoder RD2 connected to the second sub-memory body SB2 may be configured to select one of the plurality of second word lines, and the second column decoder CD2 may be configured to select a second CSL subset L_CS2-0 to U_CS2-15 among the plurality of CSLs. In an example embodiment, based on the first row decoder RD1 selecting one of the remaining first word lines except for every r-th first word line among the plurality of first word lines, the second row decoder RD2 may select a single second word line assigned to a single first word line among every r-th second word line among the plurality of second word lines.
[0165] Alternatively, in an example embodiment, based on the second row decoder RD2 selecting one of the remaining second word lines except every r-th second word line among the plurality of second word lines, the first row decoder RD1 may select a single first word line assigned to the single second word line among every r-th first word line among the plurality of first word lines.
[0166] According to the above-described embodiment, when one of the sub-banks included in a single bank operates as a normal-side sub-bank, the remaining sub-banks can operate as meta-side sub-banks. For example, a CSL subset of a meta-side sub-bank is allocated for each word line of a normal-side sub-bank, and a required normal / meta ratio can be significantly satisfied without chip size overhead.
[0167] Fig.35 is a diagram illustrating an example sub-bank configuration.
[0168] Reference Fig.35 According to example embodiments, each sub-memory bank SB included in the single memory bank described above may be configured to include a plurality of subset memory banks SSB1 to SSBN, where N may be an integer greater than 1. For example, a plurality of subset memory banks SSB1 to SSBN may be divided and arranged in a row direction d2. A word line WL connected to a row decoder RD may be connected to the plurality of subset memory banks SSB1 to SSBN. According to the above-described embodiment, when the sub-memory bank SB is a meta-side sub-memory bank SB, a portion of the word line WL may be allocated for metadata.
[0169] The CSL connected to the column decoder CD may be connected to a plurality of subset memory banks SSB1 to SSBN. The CSL may be operated individually for each of the subset memory banks SSB1 to SSBN. For example, among the CSLs, the CSL connected to a portion of the subset memory banks SSB1 to SSBN may be enabled, and the CSL connected to another portion of the subset memory banks SSB1 to SSBN may be disabled.
[0170] Fig.36 It is shown Fig.35 Schematic diagram of word line activation operation in a sub-memory configuration.
[0171] Reference Fig.36 , a case may be considered where a word line (e.g., every r-th word line) connected to a plurality of subset memory banks SSB1 to SSBN is allocated for metadata and metadata is output from the corresponding word line. For example, a sub-memory bank SB may be operated as a meta-side sub-memory bank SB. Then, according to the above-described embodiment, at least a portion (or a pair of CSLs) of a specific word line of the meta-side sub-memory bank SB may be allocated to read or write metadata corresponding to a normal data word line of the normal-side sub-memory bank SB.
[0172] In this case, when the sub-memory bank SB is configured to include a plurality of subset memory banks SSB1 to SSBN in the row direction d2, the allocated CSL CSL_A may be included in only one of the plurality of subset memory banks SSB1 to SSBN. Based on the fact that “at least a portion of the CSLs (or a pair of CSLs) of the plurality of CSL subsets is activated for one of the plurality of subset memory banks SSB1 to SSBN”, only a region corresponding to one of the subset memory banks SSB1 to SSBN may be activated in every r-th word line. Therefore, according to example embodiments, only the word lines of the subset memory banks connected to the allocated CSL CSL_A may be activated, and the word lines of the remaining subset memory banks may be disabled.
[0173] For example, in Fig.36 In the case of, the CSL CSL_A of the word line assigned to the normal side sub-memory bank SB is connected to the first subset memory bank SSB1, so that only the word line EN_WL connected to the first subset memory bank SSB1 can be activated, and the word line DIS_WL connected to the remaining memory banks SSB2 to SSBN can be disabled. Therefore, the column decoder CD can be operated to select the assigned CSL CSL_A, and the row decoder RD can be operated to activate only the word line EN_WL connected to the first subset memory bank SSB1.
[0174] According to the above-described embodiment, in the memory device, when the sub-memory bank SB is used as the meta-side sub-memory bank SB, only the word line EN_WL of the subset memory bank to which the allocated CSL CSL_A among all the sub-memory banks is connected can be operated. This is because: in this case, the CSLs of the remaining subset memory banks included in the meta-side sub-memory bank SB are not used for access to metadata. Therefore, according to the example embodiment, power consumption can be reduced during normal data and metadata access operations.
[0175] As described above, according to example embodiments, a volatile memory device for allocating specific data may be provided.
[0176] Although the present disclosure contains many specific implementation details, these should not be interpreted as limiting the scope of the protection that can be claimed. Specific features described in the context of separate embodiments in the present disclosure may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any suitable sub-combination. In addition, although the features may be described above as working in a specific combination, one or more features from the combination may be deleted from the combination in some cases, and the combination may point to a sub-combination or a variation of the sub-combination.
[0177] While example embodiments have been shown and described above, it will be apparent to those skilled in the art that modifications and variations may be made without departing from the scope of the inventive concept as defined by the appended claims.
Claims
1. A memory device, include: A first memory bank connected to a plurality of word lines and a plurality of column selection lines CSL, Among the plurality of word lines, every r-th word line in a column direction is allocated for metadata, wherein r is a positive integer.
2. The memory device according to claim 1, in, The first memory bank includes a first sub-memory bank and a second sub-memory bank divided in a row direction, and The first sub-bank is connected to a plurality of first word lines among the plurality of word lines, and the second sub-bank is connected to a plurality of second word lines among the plurality of word lines.
3. The memory device according to claim 2, in, Among the plurality of first word lines, every r-th first word line in the column direction is allocated metadata for the second sub-memory bank, and Among the plurality of second word lines, every r-th second word line in the column direction is allocated metadata for the first sub-bank.
4. The memory device according to claim 3, in, Every r-th first word line is allocated to every 1st second word line to every (r-1)th second word line among the plurality of second word lines, and Every r-th second word line is allocated to every 1st to every (r-1)th first word line among the plurality of first word lines.
5. The memory device according to claim 2, in, The first sub-bank is connected to a plurality of first CSL subsets among the plurality of CSLs, and the second sub-bank is connected to a plurality of second CSL subsets among the plurality of CSLs.
6. The memory device according to claim 5, in, The plurality of first CSL subsets and the plurality of second CSL subsets are each selected from the plurality of CSLs based on a column selection signal.
7. The memory device according to claim 5, in, At least a portion of the plurality of first CSL subsets is allocated to one of the remaining second word lines except for every r-th second word line among the plurality of second word lines, and At least a portion of the plurality of second CSL subsets is allocated to one of the remaining first word lines except for every r-th first word line among the plurality of first word lines.
8. The memory device according to claim 2, further comprising: include: a first row decoder and a first column decoder, the first row decoder being configured to select one of the plurality of first word lines, the first column decoder being configured to select a first subset of CSLs among the plurality of CSLs; as well as A second row decoder and a second column decoder, the second row decoder is configured to select one of the plurality of second word lines, and the second column decoder is configured to select a second subset of CSLs among the plurality of CSLs.
9. The memory device according to claim 8, in, Based on the first row decoder selecting a single first word line from the remaining first word lines except every r-th first word line among the plurality of first word lines, the second row decoder selects a single second word line assigned to the single first word line from every r-th second word line among the plurality of second word lines.
10. The memory device according to claim 8, in, Based on the second row decoder selecting a single second word line from the remaining second word lines except every r-th second word line among the plurality of second word lines, the first row decoder selects a single first word line assigned to the single second word line from every r-th first word line among the plurality of first word lines.
11. The memory device according to claim 1, in, r is 8 or 16.
12. The memory device according to claim 7, in, r is 8, At least a portion of the plurality of first CSL subsets is a pair of first CSL subsets, and At least a portion of the plurality of second CSL subsets is a pair of second CSL subsets.
13. The memory device according to claim 7, in, r is 16, At least a portion of the plurality of first CSL subsets is a single first CSL subset, and At least a portion of the plurality of second CSL subsets is a single second CSL subset.
14. The memory device according to any one of claims 1 to 13, in, The first memory bank is connected to a plurality of global input / output lines, and The memory device further includes a second memory bank that is adjacent to the first memory bank and disposed in a column direction of the first memory bank and is configured to share the plurality of global input / output lines with the first memory bank.
15. A memory device, include: A memory bank connected to a plurality of word lines and a plurality of column selection lines CSL; a row decoder connected to the plurality of word lines and extending in a column direction; as well as a column decoder connected to the plurality of CSLs and extending in the row direction, Among the plurality of word lines, every r-th word line in a column direction is allocated for metadata, wherein r is a positive integer.
16. The memory device according to claim 15, in, The memory bank includes a first sub-memory bank and a second sub-memory bank divided in a row direction, and The first sub-bank is connected to a plurality of first word lines among the plurality of word lines, and the second sub-bank is connected to a plurality of second word lines among the plurality of word lines.
17. The memory device according to claim 16, in, Based on selecting a single first word line from remaining first word lines except every r-th first word line among the plurality of first word lines, the row decoder selects a single second word line assigned to the single first word line from every r-th second word line among the plurality of second word lines.
18. The memory device according to claim 16, in, The first sub-memory bank is connected to a plurality of first CSL subsets among the plurality of CSLs, and the second sub-memory bank is connected to a plurality of second CSL subsets among the plurality of CSLs, and The column decoder selects at least a portion of the plurality of first CSL subsets based on a single second word line being selected from remaining second word lines except for every r-th second word line among the plurality of second word lines.
19. A memory device, include: A sub-memory bank is divided in a row direction and includes a plurality of subset memory banks each divided in a row direction; a plurality of word lines extending in a row direction and connected to the sub-memory banks, wherein, among the plurality of word lines, every r-th word line in a column direction is allocated for metadata, wherein r is a positive integer; and A plurality of column selection line subsets extend in a column direction and are connected to the sub-memory banks.
20. The memory device according to claim 19, in, Based on activating at least a portion of the plurality of subsets of column selection lines for a single subset memory bank among the plurality of subset memory banks, only a region corresponding to the single subset memory bank is activated in every r-th word line.
