Memory, control method thereof and module equipment

By using delay circuits and control circuits in memory to determine address groups in parallel processing, the memory operating frequency is improved, and the problem of limited read and write operations and precharge time in the prior art is solved.

CN119065582APending Publication Date: 2024-12-03XI AN UNIIC SEMICON CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310612470.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-26
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing memory is limited by the limits of read and write operations and pre-charge time in terms of improving the operating frequency, and it is difficult to further improve on the basis of ensuring reliability.

Method used

By introducing a delay circuit and a control circuit in the memory, it is determined whether the continuous addresses belong to the same group, delay or maintain the data access interval time according to the judgment results, and realize parallel data access and pre-charge through multiple sets of data lines.

Benefits of technology

It effectively improves the operating frequency of the memory, reduces the total duration of access operations, and takes into account the improvement of reliability and frequency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119065582A_ABST
    Figure CN119065582A_ABST
Patent Text Reader

Abstract

The invention discloses a memory, a control method thereof and module equipment. The memory comprises a delay circuit, a control circuit, K groups of data lines and a memory array, the delay circuit is connected with the control circuit, the control circuit is connected with the K groups of data lines, and K is an integer greater than or equal to 2; the storage array comprises K groups of sub-storage arrays, the K groups of sub-storage arrays correspond to K groups of addresses, and the K groups of data lines are connected with the K groups of sub-storage arrays in a one-to-one correspondence manner; wherein the delay circuit judges whether two continuous addresses belong to the same group in the K groups of addresses or not according to the received address sequence, and indicates whether the control circuit delays the interval time of data access to the plurality of addresses or not according to the judgment result, so that pre-charging can be carried out in the interval time. The invention provides a scheme which gives consideration to the working frequency and reliability of the memory.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of electronic technology, and in particular to a memory, a control method thereof, and a module device. Background Art

[0002] With the development of various electronic products, the performance requirements for memory are getting higher and higher. The operating frequency is one of the important parameters of memory. The higher the operating frequency, the faster the read and write speed of the memory.

[0003] The current method of increasing the operating frequency of memory is mainly to compress the time of "read and write" operation and / or "pre-charge" operation. However, due to the limitations of process parameters, storage array capacity, voltage, temperature and other conditions, the time of "read and write" operation and / or "pre-charge" operation has been almost compressed to the limit, making it difficult to further increase the frequency while ensuring reliability. Summary of the invention

[0004] In view of the above problems, the present invention is proposed to provide a memory, a control method thereof and a module device that overcomes the above problems or at least partially solves the above problems.

[0005] In a first aspect, a memory is provided, comprising:

[0006] A delay circuit, a control circuit, K groups of data lines and a storage array, wherein the delay circuit is connected to the control circuit, the control circuit is connected to the K groups of data lines, and K is an integer greater than or equal to 2;

[0007] The storage array includes K groups of sub-storage arrays, the K groups of sub-storage arrays correspond to K groups of addresses, and the K groups of data lines are connected to the K groups of sub-storage arrays in a one-to-one correspondence;

[0008] Among them, the delay circuit determines whether two consecutive addresses belong to the same group of the K group addresses based on the received address sequence, and instructs the control circuit whether to delay the interval time for data access to the multiple addresses based on the judgment result so as to enable pre-charging within the interval time.

[0009] Optionally, the delay circuit is also used to: if the two addresses belong to the same group among the K groups of addresses, send a delay instruction to the control circuit, the delay instruction being used to indicate delaying the time interval between data accesses to the two addresses so as to perform serial operations on a single group of addresses; if the two addresses do not belong to the same group among the K groups of addresses, send a maintain instruction to the control circuit, the maintain instruction being used to indicate maintaining the time interval between data accesses to the two addresses so as to perform parallel operations on multiple groups of addresses.

[0010] Optionally, the control circuit is also used to: when receiving a delay instruction, sequentially access and precharge the previous address of the two addresses through a group of data lines in the K groups of data lines, and after precharging the previous address, continue to sequentially access and precharge the latter address of the two addresses; when receiving a maintain instruction, sequentially access and precharge the previous address through a group of data lines in the K groups of data lines, and when precharging the previous address, parallelly control another group of data lines in the K groups of data lines to sequentially access and precharge the latter address.

[0011] Optionally, the control circuit is further used to: perform data access in sequence and in a loop according to the address sequence, wherein the two addresses are respectively the last address of the address sequence and the first address of the address sequence.

[0012] Optionally, the interval time after the delay is greater than or equal to the time required to complete a pre-charging.

[0013] Optionally, the control circuit is also used to: when data access is performed on a corresponding address through a group of data lines in the K groups of data lines, control other groups of data lines in parallel to pre-charge other addresses, wherein the other groups of data lines are data lines in the K groups of data lines except the group of data lines.

[0014] Optionally, the control circuit includes: K control sub-circuits, and the K control sub-circuits are connected to the K groups of data lines in a one-to-one correspondence to control the K groups of data lines in parallel to perform data access and pre-charge on the K groups of addresses.

[0015] In a second aspect, a control method for a memory is provided, wherein the memory comprises a delay circuit, a control circuit, K groups of data lines and a memory array, wherein the delay circuit is connected to the control circuit, and the control circuit is connected to the K groups of data lines, where K is an integer greater than or equal to 2; the memory array comprises K groups of sub-memory arrays, the K groups of sub-memory arrays correspond to K groups of addresses, and the K groups of data lines are connected to the K groups of sub-memory arrays in a one-to-one correspondence, and the method comprises:

[0016] The delay circuit determines whether two consecutive addresses belong to the same group of the K groups of addresses based on the received address sequence, and instructs the control circuit whether to delay the interval time for data access to the multiple addresses based on the determination result so as to enable precharging within the interval time.

[0017] Optionally, the method also includes: if the two addresses belong to the same group among the K groups of addresses, generating a delay instruction, wherein the delay instruction is used to indicate a delay in the time interval between data accesses to the two addresses so as to perform serial operations on a single group of addresses; if the two addresses do not belong to the same group among the K groups of addresses, generating a maintain instruction, wherein the maintain instruction is used to indicate a maintain in the time interval between data accesses to the two addresses so as to perform parallel operations on multiple groups of addresses.

[0018] Optionally, the method also includes: if a delay instruction is generated, data access and pre-charging are performed in sequence on the previous address of the two addresses through a group of data lines in the K groups of data lines, and after pre-charging the previous address, data access and pre-charging are continued in sequence on the next address of the two addresses; if a maintain instruction is generated, data access and pre-charging are performed in sequence on the previous address through a group of data lines in the K groups of data lines, and when pre-charging the previous address, another group of data lines in the K groups of data lines are controlled in parallel to perform data access and pre-charge on the next address in sequence.

[0019] Optionally, the two addresses are respectively the last address of the address sequence and the first address of the address sequence.

[0020] Optionally, the interval time after the delay is greater than or equal to the time required to complete a pre-charging.

[0021] Optionally, the method further includes: when accessing data to a corresponding address through a group of data lines in the K groups of data lines, parallelly controlling other groups of data lines to pre-charge other addresses, wherein the other groups of data lines are data lines in the K groups of data lines except the group of data lines.

[0022] According to a third aspect, a module device is provided, comprising a communication module, a power module and a storage module, wherein: the power module is used to provide power to the module device; the storage module is used to store data and instructions; the communication module is used for internal communication within the module device, or for the module device to communicate with an external device; and the storage module comprises the memory described in any one of claims 1 to 7.

[0023] The technical solution provided in the embodiments of the present invention has at least the following technical effects or advantages:

[0024] The memory, control method and module device provided by the embodiment of the present invention are configured to include K groups of data lines, the memory array of the memory includes K groups of sub-memory arrays, and the K groups of data lines are connected to the K groups of sub-memory arrays in a one-to-one correspondence, so that the control circuit can perform data access and pre-charge the K groups of sub-memory arrays in parallel through the K groups of data lines. In this way, when one group of sub-memory arrays is pre-charged, data access can be performed on another group of sub-memory arrays in parallel, reducing the total duration of the access operation and effectively improving the working frequency of the memory. In addition, by setting a delay circuit to pre-determine whether two consecutive addresses belong to the same group of K groups of addresses, and then instructing the control circuit whether to delay the interval time for data access to multiple addresses based on the judgment result, the timing problem of a group of data lines having to perform data access and pre-charging at the same time is effectively avoided, and reliability and working frequency are effectively taken into account.

[0025] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0027] Figure 1 A schematic diagram of the structure of an existing memory in an embodiment of the present invention;

[0028] Figure 2 Schematic diagram of access operation timing of a conventional memory in an embodiment of the present invention;

[0029] Figure 3 A schematic diagram of a memory structure provided in an embodiment of the present invention Figure 1 ;

[0030] Figure 4 A schematic diagram of a memory access operation timing provided in an embodiment of the present invention Figure 1 ;

[0031] Figure 5 A schematic diagram of a memory access operation timing provided in an embodiment of the present invention Figure 2 ;

[0032] Figure 6 A schematic diagram of a memory access operation timing provided in an embodiment of the present invention Figure 3 ;

[0033] Figure 7 A schematic diagram of a timing problem when two consecutive addresses are located in the same group in an embodiment of the present invention;

[0034] Figure 8 A schematic diagram of a memory structure provided in an embodiment of the present invention Figure 2 ;

[0035] Fig. 9 A schematic diagram of a memory access operation timing provided in an embodiment of the present invention Figure 4 ;

[0036] Fig.10 A schematic diagram of a memory access operation timing provided in an embodiment of the present invention Figure 5 ;

[0037] Fig.11 Schematic diagram of a delay signal of a delay circuit in an embodiment of the present invention;

[0038] Fig.12 A schematic diagram of the steps of a memory control method provided in an embodiment of the present invention Figure 1 ;

[0039] Fig.13 A schematic diagram of the steps of a memory control method provided in an embodiment of the present invention Figure 2 ;

[0040] Fig.14 A schematic diagram of the structure of a module device is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to be able to fully convey the scope of the present disclosure to those skilled in the art. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0042] Various structural schematic diagrams according to embodiments of the present disclosure are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may further design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0043] See also Figure 1 , the memory usually includes a memory array 1, a data line 2 and a control circuit 3. Each memory cell 101 in the memory array 1 is connected to the data line 2 via a bit line 102, and the control circuit 3 is connected to the data line 2. After receiving an access instruction carrying an address, the control circuit 3 performs an access operation on the memory cell corresponding to the address in the memory array 1 via the data line 2.

[0044] See also Figure 2 A complete access operation includes data access (read or write operation, hereinafter referred to as read and write) and pre-charging (setting the bit line and / or data line to a preset voltage value to facilitate subsequent read and write operations, hereinafter referred to as pre-charging. In many memory structures, due to the read and write circuit structure, the data line also needs to be set to a preset voltage value before the read and write operation). The duration of data access and pre-charging is set as needed, and can be the same or different. Only after completing a read and write and a pre-charging in sequence can the next read and write and pre-charging be performed. Therefore, the duration of an access operation includes the read and write duration and the pre-charging duration, which causes the operating frequency of the memory to be affected by the total duration of the read and write duration and the pre-charging duration, which makes it difficult to improve. For example, if Figure 2 As shown, the control circuit 3 accesses "address 0" through data line 2 to read and write "data 0", then needs to first perform the operation "read and write 0" (read and write the storage unit corresponding to address 0), and then perform the operation "precharge 0" (precharge the bit line and / or data line connected to the storage unit corresponding to address 0), and then can access "address 1", that is, perform "read and write 1" and "precharge 1" in sequence. The total duration of each access operation is equal to the read and write duration plus the precharge duration, and the next access operation can only be performed after the previous access operation is completed. The operating frequency is low and difficult to improve.

[0045] See also Figure 3 , the present application provides a memory, comprising:

[0046] Storage array 1, K groups of data lines 2 and control circuit 3. Storage array 1 includes K groups of sub-storage arrays 11, K groups of data lines 2 are connected to K groups of sub-storage arrays 11 in one-to-one correspondence (one group of data lines 2 is connected to one group of sub-storage arrays 11), and control circuit 3 is connected to K groups of data lines 2. Control circuit 3 performs data access and pre-charge on K groups of sub-storage arrays 11 in parallel through K groups of data lines 2, K being greater than or equal to 2.

[0047] Since the storage array 1 is grouped, and multiple groups of data lines 2 are set to connect different groups of sub-storage arrays 11. Therefore, when the control circuit 3 performs data access to the corresponding sub-storage array 11 through one group of data lines 2 in the K groups of data lines 2, it can control other groups of data lines 2 in parallel to precharge other sub-storage arrays 11. Here, the other groups of data lines 2 are at least one group of data lines 2 in the K groups of data lines 2 except the group of data lines 2 that are performing data access. In this way, after reading and writing an address through one group of data lines 2, it is possible to directly start reading and writing another address through another group of data lines 2 without waiting for the pre-charging time. Therefore, the duration of each access operation can be reduced to the duration of one read and write operation, saving the pre-charging time. In this way, the operating frequency of the memory is effectively improved in a parallel manner.

[0048] For example, Figure 3 As shown, the storage array 1 is divided into two groups of sub-storage arrays 11, and each group of sub-storage arrays 11 is connected to a group of data lines 2. Each group of sub-storage arrays 11 includes a plurality of storage cells 101, and each storage cell 101 is connected to a corresponding group of data lines 2 through a bit line 102. The control circuit 3 is connected to both groups of data lines 2. In this way, the control circuit 3 can perform data access and pre-charge on the two groups of sub-storage arrays 11 in parallel. Similarly, when K is greater than 2, for example, K is equal to 3, three groups of sub-storage arrays 11 can be set to be connected to the three groups of data lines 2 in a one-to-one correspondence, which is not limited here.

[0049] The control circuit 3 accesses the data of the storage array 1 according to the preset address, and K groups of sub-storage arrays can be set to correspond to K groups of addresses, that is, a group of data lines 2 can access a group of addresses. Specifically, each group of sub-storage arrays 11 includes a plurality of storage units 101, wherein N storage units 101 are one address, one address can store N bits of data, and a group of data lines 2 can only access one address in the corresponding group of addresses at a time, and N is a positive integer.

[0050] In an optional implementation, the control circuit 3 may receive a preset address sequence and access data to the storage array 1 in sequence according to the address sequence. According to the division method of the K group addresses and the ordering method of the address sequence, different access schemes may be set to balance the working efficiency and access reliability of the memory. Two schemes are listed below as examples:

[0051] The first is a situation where any two consecutive addresses in a preset address sequence are located in different groups among the K groups of addresses.

[0052] In order to realize that any two connected addresses are located in different groups, the division of K groups of addresses can be set according to the value of K. Take K equal to 2 as an example: two groups of sub-storage arrays 11 correspond to two groups of addresses, one of the two groups of addresses is the address sorted as an odd number of bits in the address sequence, and the other group of addresses is the address sorted as an even number of bits in the address sequence. For example, assuming that the address sequence is A1, A2, A3, A4...An, and the two groups of data lines 2 are S1 and S2, then A1, A3, A5... can be set to be located in the sub-storage array 11 corresponding to S1, and A2, A4, A6... can be set to be located in the sub-storage array 11 corresponding to S2, so that the two addresses connected in front and behind can be accessed simultaneously through the two groups of data lines 2 in parallel. Of course, when K is equal to 3, assuming that the three groups of data lines 2 are S1, S2 and S3, the address sequence A1, A4, A7... can be set to be located in the sub-storage array 11 corresponding to S1, A2, A5, A8... are located in the sub-storage array 11 corresponding to S2, and A3, A6, A9... are located in the sub-storage array 11 corresponding to S3. As long as any two connected addresses are located in different groups in the K group address, there is no limitation here.

[0053] Since the two connected addresses are located in different groups of the K group address, parallel access operations can be performed through different groups of data lines 2. Therefore, the memory provided by the present application can precharge the next address in parallel when accessing data to the previous address, or access data to the next address in parallel when precharging the previous address, which greatly improves the operating frequency.

[0054] In an alternative implementation, please refer to Figure 4 , the control circuit 3 first controls one group of data lines 2 in the K groups of data lines 2 to sequentially access and precharge the i-th address in the address sequence, where i is a positive integer. When precharging the i-th address, another group of data lines 2 in the K groups of data lines 2 is controlled in parallel to sequentially access and precharge the i+1-th address in the address sequence. In this way, there is no need to wait until the precharging of the i-th address is completed before accessing the data of the i+1-th address, which can significantly reduce the duration of the access operation. Through parallel control, the average access duration of each address is reduced to the duration of one data access, saving the time consumed by precharging.

[0055] For example, Figure 4As shown, assuming that K is equal to 2, the control circuit 3 accesses "address 0" through the first group of data lines 2 to read and write "data 0". It is necessary to first perform the operation "read and write 0" (read and write the storage unit corresponding to address 0), and then perform the operation "pre-charge 0" (pre-charge the bit line and / or data line connected to the storage unit corresponding to address 0). When the first group of data lines 2 performs the operation "pre-charge 0", the second group of data lines 2 accesses "address 1" in parallel, that is, "read and write 1" and "pre-charge 1" are performed in sequence. When the second group of data lines 2 performs the operation "pre-charge 1", the first group of data lines 2 accesses "address 2" in parallel, that is, "read and write 2" and "pre-charge 2" are performed in sequence. By performing access operations alternately and in parallel by two groups of data lines 2, the working efficiency of the memory can be greatly improved. Assuming that the pre-charge duration accounts for 30% of the total time of an access operation (data access plus pre-charge), if using Figure 4 The parallel access method shown can increase the operating frequency of the memory by about 30%.

[0056] Of course, you can also Figure 5 As shown, the control circuit 3 first controls one group of data lines 2 in the K groups of data lines 2 to sequentially precharge and access data to the i-th address in the address sequence. When accessing data to the i-th address, another group of data lines 2 in the K groups of data lines 2 is controlled in parallel to sequentially precharge and access data to the i+1-th address in the address sequence, which is not limited here.

[0057] Of course, when K is greater than 2, the access method to the storage array 1 can also be set according to the division method of the K group addresses and the sorting method of the address sequence. It only needs to satisfy the requirements that the address access operation is performed in the order of the address sequence and that any two consecutive addresses are located in different groups in the K group addresses. No limitation is made here.

[0058] For example, when K is equal to 3, Figure 6 As shown, the first group of data lines 2 in the K groups of data lines 2 are first controlled to perform precharging and data access to the i-th address in the address sequence in sequence (or data access and precharging are performed in sequence, which is not limited here). When data access is performed to the i-th address, the second group of data lines 2 are controlled in parallel to perform precharging and data access to the i+1-th address in the address sequence in sequence. When data access is performed to the i+1-th address, the third group of data lines 2 are controlled in parallel to perform precharging and data access to the i+2-th address in the address sequence in sequence. Of course, the first group of data lines 2 and the second group of data lines 2 in the K groups of data lines 2 can also be controlled to perform access operations alternately and in parallel, and then the second group of data lines 2 and the third group of data lines 2 can be controlled to perform access operations alternately and in parallel.

[0059] The second situation is that there are two consecutive addresses in the preset address sequence and both of them are located in the same group of K groups of addresses.

[0060] In some address sequences, there may be two consecutive addresses in the same group. For example, when data is accessed in a loop according to the address sequence, there may be an address boundary (two consecutive addresses are the last address of the address sequence and the first address of the address sequence). For example, suppose the address sequence is A1, A2, A3, A4...A99, A1, A3, A5...A99 are located in the sub-storage array 11 corresponding to the first group of data lines 2, and A2, A4, A6...A98 are located in the sub-storage array 11 corresponding to the second group of data lines 2. After looping to A99, it is necessary to continue to access A1, and A99 and A1 are in the same group. For another example, when the address sequence is updated according to demand, the updated address sequence may have two consecutive addresses in the same group.

[0061] In this case, if the above Figures 4 to 6 If the access operation is performed according to the timing of alternating access of different groups of data lines as shown, the following will occur: Figure 7 The timing problem shown. That is, assuming that "address 0" and "address 1" are connected and in the same group of addresses, while "address 0" is sequentially "read and write 0" and "precharge 0", "address 1" will be started, which will cause the group of data lines 2 to execute "precharge 0" and "read and write 1" at the same time, which does not meet the timing requirements and will cause data access errors.

[0062] To solve the above problems, the present application also provides a memory, such as Figure 8 As shown, including:

[0063] The delay circuit 4, the control circuit 3, the K groups of data lines 2 and the storage array 1, the delay circuit 4 is connected to the control circuit 3, the control circuit 3 is connected to the K groups of data lines 2, K is an integer greater than or equal to 2. The storage array 1 includes K groups of sub-storage arrays 11, the K groups of sub-storage arrays 11 correspond to K groups of addresses, and the K groups of data lines 2 are connected to the K groups of sub-storage arrays 11 in a one-to-one correspondence. The delay circuit 4 determines whether two consecutive addresses belong to the same group of the K groups of addresses according to the received address sequence, and instructs the control circuit 3 whether to delay the interval time for data access to multiple addresses according to the determination result, so as to perform precharging within the interval time.

[0064] On the one hand, since the storage array 1 is grouped and multiple groups of data lines 2 are set to connect sub-storage arrays 11 of different groups, it is possible to achieve that when the control circuit 3 performs data access to the corresponding sub-storage array 11 through a group of data lines 2 in the K groups of data lines 2, it can control other groups of data lines 2 in parallel to precharge other sub-storage arrays 11. Here, the other groups of data lines 2 are at least one group of data lines 2 in the K groups of data lines 2 except the group of data lines 2 that are currently accessing data. In this way, the operating frequency of the memory is effectively improved in a parallel manner. On the other hand, it is also considered that in some address sequences, there may be two connected addresses in the same group. In order to avoid the problem of data access errors caused by the timing sequence of all parallel alternating accesses when two connected addresses are in the same group, a delay circuit 4 can be set to be connected to the control circuit 3, and the delay circuit 4 can be used to pre-judge whether two consecutive addresses belong to the same group in the K group of addresses, and then indicate whether to delay the interval time for data access to multiple addresses according to the judgment result, so that precharging can be performed in the interval time, effectively avoiding the timing problem of a group of data lines 2 having to perform data access and precharging at the same time.

[0065] It can be seen that the combination of the grouping of the memory array 1, the setting of the multiple groups of data lines 2 and the setting of the delay circuit 4 can effectively take into account both the operating frequency and the reliability of the memory.

[0066] In an optional implementation, the delay interval can be set to be greater than or equal to the time required to complete a precharge, so as to ensure that the precharge can be completed in the gap between two data accesses, avoid the overlap of the precharge operation of the previous address and the data access operation of the next address in timing, and further ensure reliability.

[0067] In a specific implementation process, the interval time may be a fixed duration preset based on an empirical value, or may be a duration adjusted in real time based on a received timing parameter, which is not limited here.

[0068] In an alternative embodiment, Figure 8The memory shown is provided with a delay circuit 4. In order to take into account both the operating frequency and reliability, the delay circuit 4 will first judge the received address sequence during the access operation. If the two connected addresses belong to the same group in the K group address, it means that the access to the two addresses is a serial operation of a single group (the same group) of addresses that needs to be successively executed by the same group of data lines 2, and then a delay instruction is sent to the control circuit 3. The delay instruction is used to indicate the time interval between delaying the data access to the two addresses, so that the data access to the next address can be performed after precharging in the delayed time interval, avoiding timing problems. If the delay circuit 4 determines that the two addresses do not belong to the same group in the K group address, a maintenance instruction is sent to the control circuit 3. The maintenance instruction is used to indicate the time interval between maintaining the data access to the two addresses, so as to perform parallel operations on multiple groups of addresses and improve work efficiency.

[0069] In an optional implementation, the way to access an address may be to sequentially access data and precharge the address, or to sequentially precharge and access data the address. Take data access first and then precharge as an example: when the control circuit 3 receives a delay instruction, it sequentially accesses data and precharges the first address of the two addresses through a group of data lines in the K groups of data lines, and after precharging the first address, it continues to sequentially access data and precharge the second address of the two addresses. When the control circuit 3 receives a maintain instruction, it sequentially accesses data and precharges the first address through a group of data lines in the K groups of data lines, and when precharging the first address, it controls in parallel another group of data lines in the K groups of data lines to sequentially access data and precharge the second address.

[0070] For example, Fig. 9 As shown, assuming that K is equal to 2, assuming that the address sequence is: address 0", "address 1", "address 2", "address 3", etc., wherein "address 0", "address 1" and "address 3" all belong to the first group of addresses, and "address 2" belongs to the second group of addresses. After the delay circuit 4 receives the address sequence, it determines that "address 0" and "address 1" are connected and located in the same group of addresses, and then sends a delay instruction to the control circuit 3 to control the first group of data lines 2 to delay for a period of time after "reading and writing 0" to "address 0" ( Fig. 9The dotted box in the figure is the time interval of the delay), and "pre-charge 0" is performed on "address 0" within the time interval, so that "read and write 1" and "pre-charge 1" of "address 1" can be started after "pre-charge 0" is completed. Next, the delay circuit 4 determines that "address 1" and "address 2" do not belong to the same group of addresses, and it will send a maintenance instruction to the control circuit 3 to control the timing of maintaining alternating parallel access, that is, when the first group of data lines 2 performs the operation "pre-charge 1", the second group of data lines 2 access "address 2" in parallel, that is, "read and write 2" and "pre-charge 2" are performed in sequence. The delay circuit 4 continues to determine that "address 2" and "address 3" do not belong to the same group of addresses, and it will continue to send a maintenance instruction to the control circuit 3. When the second group of data lines 2 performs the operation "pre-charge 2", the first group of data lines 2 access "address 3" in parallel, that is, "read and write 3" and "pre-charge 3" are performed in sequence. By combining the delay circuit 4 to determine the grouping of the address sequence and sending the delay signal and the maintenance signal according to the determination result to adjust the serial access and the parallel access, the correctness of the timing under various address sequences is ensured and the working efficiency of the memory is improved.

[0071] Of course, you can also Fig.10 As shown, one address is precharged first, and then data is accessed to the address. That is, when the delay circuit 4 determines that the two addresses are continuous and belong to the same group, the control circuit 3 performs precharge and data access to the two addresses in series. When the delay circuit 4 determines that the two addresses are continuous and do not belong to the same group, the control circuit 3 first uses a group of data lines 2 to precharge and data access the previous address in sequence, and then when accessing data to the previous address, another group of data lines 2 is used in parallel to precharge the next address.

[0072] Of course, when K is greater than 2, the delay circuit 4 can also be used to first judge the received address sequence and then send a delay signal or a maintenance signal to take into account the working frequency and reliability of the memory.

[0073] In an optional implementation, the delay signal and the hold signal sent by the delay circuit 4 can be set as required. Fig.11 As shown, the delay signal can be set to "1" (high level) and the maintenance signal can be set to "0" (low level). Of course, the delay signal can also be set to "0" and the maintenance signal can be set to "1", which is not limited here.

[0074] In an optional embodiment, considering that a memory has been pre-divided into K groups of sub-storage arrays 11, K groups of data lines 2, and K groups of addresses, the situation where two consecutive addresses belong to the same group of addresses often occurs at a specific position in the address sequence, for example, the address boundary situation occurs at the last address and the first address in the address sequence. Therefore, the delay circuit 4 can be set to perform grouping judgment only on the preset specific continuous addresses, for example, only the last address and the first address of the address sequence are judged whether they are in the same address group, and a delay signal or a maintenance signal is output according to the judgment result, and other addresses are not judged and the maintenance signal is directly output. Thereby reducing the judgment steps of the delay circuit 4 and saving computing resources. Of course, all continuous addresses in the address sequence can also be judged in groups, which is not limited here.

[0075] Of course, other access schemes may be set according to different ways of dividing the K groups of addresses and sorting the address sequences, not limited to the two listed above.

[0076] In an optional embodiment, the control circuit 3 at least includes a data read function module (used to read data stored in a storage unit), a data write function module (used to write data to be stored in a storage unit), a precharge function module (used to precharge the bit line and / or data line connected to the storage unit), a data selection function module (used to select and arrange the data to be read or written in sequence according to the address sequence), a column address decoding function module (used to decode the received address sequence to find the storage unit corresponding to the address) and a timing control function module (used to adjust the timing of the access operation after receiving the delay signal of the delay circuit 4). The delay circuit 4 at least includes an address grouping judgment function module (used to judge whether consecutive addresses belong to the same group) and a signal generation function module (used to generate a delay signal or a maintenance signal according to the judgment result).

[0077] In an optional embodiment, the control circuit 3 may include K control subcircuits, which are connected to K groups of data lines 2 in a one-to-one correspondence, so as to control the K groups of data lines 2 in parallel to access and precharge the K groups of addresses. That is to say, each control subcircuit has an independent read function module, a data write function module and a precharge function module. Of course, it is also possible not to set up multiple control subcircuits, but to improve the circuit of the control circuit of a single group of data lines, and add some functional modules to realize that the control circuit 3 can control the K groups of data lines 2 in parallel, which is not limited here.

[0078] In the specific implementation process, the delay circuit 4 can be a dedicated integrated circuit chip with a delay function, or a programmable device. The control circuit 3 can also be a dedicated integrated circuit chip or a programmable device. The delay circuit 4 can be integrated with the control circuit 3 on a chip, or can be a discrete circuit chip, which is not limited here and will not be listed one by one.

[0079] Based on the same inventive concept, an embodiment of the present invention further provides a method for controlling a memory, wherein the memory is as follows: Figure 3 As shown, it includes a storage array 1, K groups of data lines 2 and a control circuit 3. The storage array 1 includes K groups of sub-storage arrays 11, the K groups of data lines 2 are connected to the K groups of sub-storage arrays 11 in a one-to-one correspondence, and the control circuit 3 is connected to the K groups of data lines 2, wherein K is greater than or equal to 2, as shown in FIG. Fig.12 As shown, the method includes:

[0080] Step 1201, when accessing data to the corresponding sub-storage array through one group of data lines in the K groups of data lines, parallelly control other groups of data lines to precharge other sub-storage arrays, wherein the other groups of data lines are at least one group of data lines in the K groups of data lines except the group of data lines.

[0081] In an optional embodiment, the method further includes: accessing data in sequence according to a preset address sequence, wherein the K groups of sub-storage arrays correspond to K groups of addresses, and any two connected addresses in the address sequence are located in different groups of the K groups of addresses.

[0082] In an optional embodiment, the method further includes: accessing data in sequence according to a preset address sequence, wherein the K groups of sub-storage arrays correspond to K groups of addresses, one group of addresses in the K groups of addresses are addresses sorted as odd bits in the address sequence, and the other group of addresses are addresses sorted as even bits in the address sequence, and K is 2.

[0083] In an optional embodiment, the sequential data access includes: controlling a group of data lines in the K groups of data lines to sequentially access and precharge the i-th address in the address sequence, where i is a positive integer; when precharging the i-th address, controlling another group of data lines in the K groups of data lines in parallel to sequentially access and precharge the i+1-th address in the address sequence.

[0084] In an optional embodiment, the control circuit includes K control sub-circuits, and the K control sub-circuits are connected to the K groups of data lines in a one-to-one correspondence. The method also includes: controlling the K groups of data lines through the K control sub-circuits to perform data access and pre-charge on the K groups of sub-storage arrays in parallel.

[0085] Based on the same inventive concept, an embodiment of the present invention further provides a method for controlling a memory, wherein the memory is as follows: Figure 8 As shown, it includes a delay circuit 4, a control circuit 3, K groups of data lines 2 and a storage array 1, the delay circuit 4 is connected to the control circuit 3, the control circuit 3 is connected to the K groups of data lines 2, K is an integer greater than or equal to 2. The storage array 1 includes K groups of sub-storage arrays 11, the K groups of sub-storage arrays 11 correspond to K groups of addresses, the K groups of data lines 2 are connected to the K groups of sub-storage arrays 11 in a one-to-one correspondence, and the method is as follows Fig.13 As shown, including:

[0086] Step 1301, the delay circuit determines whether two consecutive addresses belong to the same group of K groups of addresses based on the received address sequence, and instructs the control circuit whether to delay the interval time for data access to multiple addresses based on the determination result so as to enable precharging within the interval time.

[0087] In an optional embodiment, the method further includes: if the two addresses belong to the same group among the K groups of addresses, generating a delay instruction, wherein the delay instruction is used to indicate a delay in the time interval between data accesses to the two addresses so as to perform serial operations on a single group of addresses; if the two addresses do not belong to the same group among the K groups of addresses, generating a maintain instruction, wherein the maintain instruction is used to indicate a maintain in the time interval between data accesses to the two addresses so as to perform parallel operations on multiple groups of addresses.

[0088] In an optional embodiment, the method also includes: if a delay instruction is generated, data access and pre-charging are performed in sequence on the first address of the two addresses through a group of data lines in the K groups of data lines, and after pre-charging the first address, data access and pre-charging are continued in sequence on the second address of the two addresses; if a maintain instruction is generated, data access and pre-charging are performed in sequence on the first address through a group of data lines in the K groups of data lines, and when pre-charging the first address, another group of data lines in the K groups of data lines are controlled in parallel to perform data access and pre-charge on the second address in sequence.

[0089] In an optional embodiment, the two addresses are respectively the last address of the address sequence and the first address of the address sequence.

[0090] In an optional embodiment, the interval time after the delay is greater than or equal to the time required to complete a pre-charging operation.

[0091] In an optional embodiment, the method further includes: when accessing data to a corresponding address through a group of data lines in the K groups of data lines, parallelly controlling other groups of data lines to pre-charge other addresses, wherein the other groups of data lines are data lines in the K groups of data lines except the group of data lines.

[0092] Based on the same inventive concept, the embodiment of the present invention further provides a module device 1400, such as Fig.14 As shown, the module device 1400 includes a communication module 1401, a power module 1402 and a storage module 1403, wherein: the power module 1402 is used to provide power to the module device; the storage module 1403 is used to store data and instructions; the communication module 1401 is used for internal communication of the module device, or for the module device to communicate with external devices; the storage module 1403 includes any memory provided by the embodiments of the present invention.

[0093] The technical solution provided in the embodiments of the present invention has at least the following technical effects or advantages:

[0094] The memory, control method and module device provided by the embodiment of the present invention are configured to include K groups of data lines, the memory array of the memory includes K groups of sub-memory arrays, and the K groups of data lines are connected to the K groups of sub-memory arrays in a one-to-one correspondence, so that the control circuit can perform data access and pre-charge the K groups of sub-memory arrays in parallel through the K groups of data lines. In this way, when one group of sub-memory arrays is pre-charged, data access can be performed on another group of sub-memory arrays in parallel, reducing the total duration of the access operation and effectively improving the working frequency of the memory. In addition, by setting a delay circuit to pre-determine whether two consecutive addresses belong to the same group of K groups of addresses, and then instructing the control circuit whether to delay the interval time for data access to multiple addresses based on the judgment result, the timing problem of a group of data lines having to perform data access and pre-charging at the same time is effectively avoided, and reliability and working frequency are effectively taken into account.

[0095] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0096] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0097] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0098] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0099] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0100] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "one" or "an" preceding a component does not exclude the presence of a plurality of such components. The present invention may be implemented by means of hardware comprising a number of different components and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

Claims

1. A memory, It is characterized in that include: A delay circuit, a control circuit, K groups of data lines and a storage array, wherein the delay circuit is connected to the control circuit, the control circuit is connected to the K groups of data lines, and K is an integer greater than or equal to 2; The storage array includes K groups of sub-storage arrays, the K groups of sub-storage arrays correspond to K groups of addresses, and the K groups of data lines are connected to the K groups of sub-storage arrays in a one-to-one correspondence; Among them, the delay circuit determines whether two consecutive addresses belong to the same group of the K group addresses based on the received address sequence, and instructs the control circuit whether to delay the interval time for data access to the multiple addresses based on the judgment result so as to enable pre-charging within the interval time.

2. The memory according to claim 1, It is characterized in that The delay circuit is also used for: If the two addresses belong to the same group in the K groups of addresses, a delay instruction is sent to the control circuit, wherein the delay instruction is used to indicate a time interval between delaying data accesses to the two addresses so as to perform a serial operation of a single group of addresses; If the two addresses do not belong to the same group in the K groups of addresses, a maintenance instruction is sent to the control circuit, wherein the maintenance instruction is used to instruct to maintain the time interval between data accesses to the two addresses so as to perform parallel operations on multiple groups of addresses.

3. The memory as claimed in claim 2, It is characterized in that The control circuit is also used for: When a delay instruction is received, data access and precharge are sequentially performed on a first address of the two addresses through a group of data lines in the K groups of data lines, and after precharging the first address, data access and precharge are continued sequentially on a second address of the two addresses; When a maintenance instruction is received, data access and pre-charging are performed on the previous address in sequence through one group of data lines in the K groups of data lines, and when pre-charging the previous address, another group of data lines in the K groups of data lines are controlled in parallel to access and pre-charge the subsequent address in sequence.

4. The memory as claimed in claim 3, It is characterized in that The control circuit is also used for: Data access is performed in sequence and in a cycle according to the address sequence, wherein the two addresses are respectively the last address of the address sequence and the first address of the address sequence.

5. The memory according to claim 1, It is characterized in that The delayed interval time is greater than or equal to the time required to complete one pre-charging.

6. The memory according to any one of claims 1 to 5, It is characterized in that The control circuit is also used for: When accessing data to a corresponding address through one group of data lines in the K groups of data lines, other groups of data lines are controlled in parallel to precharge other addresses, wherein the other groups of data lines are data lines in the K groups of data lines except the one group of data lines.

7. The memory according to any one of claims 1 to 5, It is characterized in that The control circuit comprises: K control subcircuits are connected to the K groups of data lines in a one-to-one correspondence, so as to control the K groups of data lines in parallel to perform data access and pre-charge on the K groups of addresses.

8. A method for controlling a memory, It is characterized in that The memory comprises a delay circuit, a control circuit, K groups of data lines and a storage array, wherein the delay circuit is connected to the control circuit, the control circuit is connected to the K groups of data lines, and K is an integer greater than or equal to 2; the storage array comprises K groups of sub-storage arrays, the K groups of sub-storage arrays correspond to K groups of addresses, and the K groups of data lines are connected to the K groups of sub-storage arrays in a one-to-one correspondence, and the method comprises: The delay circuit determines whether two consecutive addresses belong to the same group of the K groups of addresses based on the received address sequence, and instructs the control circuit whether to delay the interval time for data access to the multiple addresses based on the determination result so as to enable precharging within the interval time.

9. The control method according to claim 8, It is characterized in that Also includes: If the two addresses belong to the same group in the K groups of addresses, a delay instruction is generated, wherein the delay instruction is used to indicate a time interval between delaying data access to the two addresses so as to perform a serial operation of a single group of addresses; If the two addresses do not belong to the same group in the K groups of addresses, a maintenance instruction is generated, wherein the maintenance instruction is used to instruct to maintain the time interval between data accesses to the two addresses so as to perform parallel operations on multiple groups of addresses.

10. The control method according to claim 9, It is characterized in that Also includes: If a delay instruction is generated, data access and precharging are sequentially performed on a first address of the two addresses through a group of data lines in the K groups of data lines, and after precharging the first address, data access and precharging are continued sequentially on a second address of the two addresses; If a maintenance instruction is generated, data access and pre-charge are performed on the previous address in sequence through one group of data lines in the K groups of data lines, and when the previous address is pre-charged, another group of data lines in the K groups of data lines are controlled in parallel to access and pre-charge the subsequent address in sequence.

11. The control method according to claim 10, It is characterized in that The two addresses are respectively the last address of the address sequence and the first address of the address sequence.

12. The control method according to claim 8, It is characterized in that The delayed interval time is greater than or equal to the time required to complete one pre-charging.

13. The control method according to any one of claims 8 to 12, It is characterized in that Also includes: When accessing data to a corresponding address through one group of data lines in the K groups of data lines, other groups of data lines are controlled in parallel to precharge other addresses, wherein the other groups of data lines are data lines in the K groups of data lines except the one group of data lines.

14. A module device, It is characterized in that The module device includes a communication module, a power module and a storage module, wherein: the power module is used to provide power to the module device; the storage module is used to store data and instructions; the communication module is used for internal communication within the module device, or for the module device to communicate with external devices; the storage module includes the memory described in any one of claims 1 to 7.