Variable-length data block cache implementation method, device and storage medium

Abstract

The present invention provides a cache implementation method, device and storage medium for variable-length data blocks. The method comprises: based on the table number of a user parameter table, querying a cache parameter table and a tag path table to obtain a tag path entry number, a tag number, a tag table base address and a data table base address corresponding to the user parameter table; the tag number is used to indicate the size of the user parameter table; the cache parameter table also includes the data length of the data to be stored corresponding to the user parameter table; based on the tag path entry number and the tag table base address, obtaining the tag table address and accessing the tag table, and in the case where there is a blank position in the tag path corresponding to the tag path entry number, determining that the blank position corresponds to the first index of the data table; determining the first address of the data table based on the first index and the data table base address, and storing the data to be stored in the data table; the problem of wasting cache capacity when the length of the data read each time is set to be the same and the read data block is small can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic equipment, and in particular to a cache implementation method, device and storage medium for variable-length data blocks. Background Art

[0002] When the hardware processor wants to store data in the memory, if the bandwidth of the hardware processor to transmit data is significantly different from the bandwidth of the memory, it is necessary to add a small cache between the memory and the hardware to store the data, namely, CACHE, to reduce the number of times the hardware accesses the memory. When the hardware transmits data, the transmitted data is often not continuous in space, and the length of the accessed data is also different. Therefore, a method is needed to accurately control the data in the cache, which can not only shorten the time to read the memory, but also effectively improve the space occupancy of the cache.

[0003] At present, the traditional method includes: when the hardware processor wants to read the target data from the memory, it first searches for the target data in the cache. If the target data cannot be found in the cache, it accesses the memory, reads out the entire data block containing the target data, and stores it in the cache.

[0004] However, when the entire data block containing the target data is read out and stored in the cache, the data is generally continuous and of fixed length. Since the cache capacity is limited, if the length of each data read is set to the same, then when the read data block is small, there will be a problem of wasting cache capacity. Summary of the invention

[0005] In view of this, the embodiments of the present invention provide a method, device and storage medium for implementing a cache of a variable-length data block to eliminate or improve one or more defects in the prior art. The problem that if the length of each read data is set to be the same, the cache capacity will be wasted when the read data block is small can be solved.

[0006] One aspect of the present invention provides a method for implementing a cache of a variable-length data block, the method comprising the following steps:

[0007] Based on the table number of the user parameter table, query the cache parameter table to obtain the number of tags, the tag table base address and the data table base address corresponding to the user parameter table; the number of tags is used to indicate the size of the user parameter table; the cache parameter table also includes the data length of the data to be stored corresponding to the user parameter table;

[0008] Based on the table number of the user parameter table, query the tag path table to obtain the tag path entry number corresponding to the user table;

[0009] Based on the tag path entry number and the tag table base address, obtain the tag table address;

[0010] accessing the tag table based on the tag table address, and determining that the blank position corresponds to a first index of the data table if there is a blank position in the tag path corresponding to the tag path entry number;

[0011] Determine a first address of the data table based on the first index and the data table base address;

[0012] According to the first address of the data table, the data to be stored is stored in the data table.

[0013] Optionally, when there is no blank position in the marking path corresponding to the marking path entry number, the method further includes:

[0014] According to the number of marks, access the mark table and query the next mark path in turn to determine whether there is a blank position;

[0015] In the case that a blank position exists, a step of determining that the blank position corresponds to a first index of the data table is performed.

[0016] Optionally, when the access is complete and there is no empty location, storage failure information is generated and returned.

[0017] Optionally, after determining that the blank position corresponds to the first index of the data table, the method further includes: storing the table number corresponding to the user parameter table, the table item number of each item in the user parameter table and the valid identifier of the user parameter table in a tag table.

[0018] Optionally, after storing the data to be stored in the data table according to the address of the data table, the method further includes:

[0019] comparing the table entry number with the table entry number stored in the tag path corresponding to the tag path entry number, and determining that the storage location of the table entry number corresponds to the second index of the data table if the table entry number exists in the stored table entry number;

[0020] Determine a second address of the data table according to the second index and the data table base address;

[0021] Based on the second address of the data table, data is read from the data table.

[0022] Optionally, when the entry number does not exist in the entry numbers stored in the tag table, the method further includes:

[0023] Traverse the tag path in the tag table;

[0024] In the case where it is determined that the table entry number is found, a step of determining that the storage location of the table entry number corresponds to the second index of the data table is performed.

[0025] Optionally, when the entry number of the queried table item is not determined, query failure information is generated and returned.

[0026] Optionally, after storing the data to be stored in the data table according to the address of the data table, the method further includes:

[0027] The table entry number is compared with the table entry number stored in the tag path corresponding to the tag path entry number. If the table entry number exists in the stored table entry number, the valid flag corresponding to the table entry number is determined to be set to 0, and the data corresponding to the table entry number is deleted.

[0028] Another aspect of the present invention provides a cache implementation device for variable-length data blocks, including a processor and a memory, wherein computer instructions are stored in the memory, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the device implements the steps of the above-mentioned cache implementation method for variable-length data blocks.

[0029] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the program implements the steps of the above-mentioned variable-length data block cache implementation method.

[0030] The variable length data block cache implementation method, device and storage medium of the present invention can solve the problem that if the length of each data read is set to be the same, then the cache capacity will be wasted when the data block read is small; through the table number of the user parameter table, the cache parameter table is queried to obtain the number of tags, the tag table base address and the data table base address corresponding to the user parameter table; the number of tags is used to indicate the size of the user parameter table; the cache parameter table also includes the data length of the data to be stored corresponding to the user parameter table; based on the table number of the user parameter table, the tag path table is queried to obtain the tag path entry number corresponding to the user table; based on the tag path entry number and the tag table base address, the tag table address is obtained; based on The tag table address is used to access the tag table, and when there is a blank position in the tag path corresponding to the tag path entry number, it is determined that the blank position corresponds to the first index of the data table; based on the first index and the data table base address, the first address of the data table is determined; according to the first address of the data table, the data to be stored is stored in the data table; by classifying the data in the form of a user parameter table structure, configuring the attributes of each user parameter table, controlling the size of the user parameter table by configuring tag_num, and controlling the length of the data by configuring data_len, the length of the data in the cache can be made variable, thereby avoiding wasting the cache capacity and improving the space utilization of the cache; at the same time, the query efficiency to the memory is improved.

[0031] Furthermore, by implementing three-level address mapping through the data table base address or tag table base address, entry number and index, it is possible to provide accuracy query of data query.

[0032] Additional advantages, purposes, and features of the present invention will be described in part in the following description, and will become apparent to those skilled in the art after studying the following, or may be learned from the practice of the present invention. The purposes and other advantages of the present invention may be achieved and obtained by the structures specifically indicated in the specification and the accompanying drawings.

[0033] Those skilled in the art will appreciate that the objectives and advantages that can be achieved with the present invention are not limited to the above specific description, and the above and other objectives that can be achieved by the present invention will be more clearly understood from the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of the present application, and do not constitute a limitation of the present invention. In the drawings:

[0035] Figure 1 A flow chart of a method for implementing a cache of a variable-length data block provided by an embodiment of the present invention;

[0036] Figure 2 A schematic diagram of the structures of a cache parameter table, a tag table and a data table provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0038] It should also be noted that, in order to avoid obscuring the present invention due to unnecessary details, only structures and / or processing steps closely related to the solutions according to the present invention are shown in the accompanying drawings, while other details that are not closely related to the present invention are omitted.

[0039] It should be emphasized that the term “include / comprises” when used herein refers to the presence of features, elements, steps or components, but does not exclude the presence or addition of one or more other features, elements, steps or components.

[0040] It should also be noted that, unless otherwise specified, the term “connection” herein may refer not only to a direct connection but also to an indirect connection involving an intermediate.

[0041] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the accompanying drawings, the same reference numerals represent the same or similar components, or the same or similar steps.

[0042] The following is an introduction to the cache implementation method of the variable-length data block provided by this application.

[0043] like Figure 1 As shown, the embodiment of the present application provides a method for implementing a cache of a variable-length data block. The execution subject of the method can be an electronic device, and the electronic device can be a terminal such as a computer, a mobile phone, a tablet computer, a personal computer, or a server. The embodiment does not limit the implementation method of the electronic device. The method includes at least steps S101 to S106:

[0044] Step S101, based on the table number of the user parameter table, query the cache parameter table to obtain the number of tags corresponding to the user parameter table, the tag table base address and the data table base address.

[0045] Among them, the table number of the user parameter table corresponds to the user parameter table one by one, and is used to uniquely indicate the user parameter table, such as Figure 2 As shown, the table number of the user parameter table can be table0, table1 or table2, etc.; in actual implementation, the table number of the user parameter table can also be numbers, letters or a combination of numbers and letters.

[0046] In this embodiment, data is classified according to the structure of the user parameter table. Each user parameter table occupies a fixed cache. Each user parameter table has at least one table item. Each table item is assigned an item number. The data in the user parameter table is accessed each time by accessing the table item number.

[0047] At the same time, the cache is divided into tables, and the structure is as follows Figure 2 As shown in the figure, it includes cache parameter table, tag table and data table, as well as tagway table for storing index resources pointing to tag table. Each table corresponds to a random access memory (RAM). Each table has its own attributes, and a total of 256 tables are supported.

[0048] In this embodiment, the cache parameter table is used to store the attributes of each user parameter table, such as Figure 2As shown, it includes the table number (table) of the user parameter table, the base address of the tag table of the user parameter table in the tag table (tag_base), the number of tags occupied by the user parameter table in the tag table (tag_num), the relevant attributes of the user parameter table (tag_type, such as ordinary index table, array table or hash table), the base address of the data table of the user parameter table in the data table (data_base) and tag_way0 to tag_way3, which represent the base addresses of the four-way tags. The number of tag ways is determined by tag_num / 8 (32), which is used to record the time sequence of which way has the longest unused tag, such as Figure 2 As shown, the hash table has 8 rows per way and the array table has 32 rows per way.

[0049] For example: taking the table number of the user parameter table as table1, set the tag table base address of table1 to 1, the number of tags to 2, the data table base address to 0, the data length to 128B, the tag path (the corresponding RAM is the tag path RAM) contains 8 tags, and the bit width of the data table (the corresponding RAM is the data RAM) is 32B. The space occupied by table1 in the cache is: the tag table (the corresponding RAM is the tag RAM) occupies 2 rows, and the data table (the corresponding RAM is the data RAM) occupies 64 rows.

[0050] The tag number (tag_num) is used to indicate the size of the user parameter table; the cache parameter table also includes the data length (data_len) of the data to be stored corresponding to the user parameter table. By configuring the tag number and data length, the space occupied by each user parameter table and the length of the data can be controlled, so as to achieve the purpose of variable length of data in the cache.

[0051] In this embodiment, the data table is used to store the data to be stored in the cache for each user parameter table; since the data table corresponds to the data RAM, storing the data in the data table means storing the data in the data RAM.

[0052] The tag table is used to store the index pointing to the data table, the entry number of the user parameter table, and the valid flag of the user parameter table data, collectively referred to as tag. A row in the tag table is called a tag path. Each tag path contains at least one tag, which can be configured through macro definition, that is, pointing to data in at least one data table. Each user parameter table contains at least one tag way. The tag path table is used to store index resources pointing to the tag table.

[0053] Step S102, based on the table number of the user parameter table, query the mark path table to obtain the mark path entry number corresponding to the user table.

[0054] Step S103, obtaining the label table address based on the label path entry number and the label table base address.

[0055] In this embodiment, the tag path entry number is added to the tag table base address to obtain the tag table address.

[0056] Step S104: access the tag table based on the tag table address, and if there is a blank position in the tag path corresponding to the tag path entry number, determine that the blank position corresponds to the first index of the data table.

[0057] In this embodiment, after determining that the blank position corresponds to the first index of the data, it can be considered that the data to be stored corresponding to the user parameter table can be stored. Based on this, in order to ensure that the data to be stored can be queried or deleted later, the query data of the user parameter table needs to be stored in the tag table, wherein the query data includes the table number corresponding to the user parameter table, the table item number of each item in the user parameter table, and the valid identifier of the user parameter table.

[0058] Specifically, after determining that the blank position corresponds to the first index of the data table, the method further includes: storing the table number corresponding to the user parameter table, the table item number of each item in the user parameter table and the valid identifier of the user parameter table into the tag table.

[0059] In addition, when there is no blank position in the tag path corresponding to the tag path entry number, it is necessary to query the next tag path in sequence according to the number of tags until a blank position is found to determine that the blank position corresponds to the first index of the data table.

[0060] Specifically, when there is no blank position in the tag path corresponding to the tag path entry number, it also includes: accessing the tag table according to the number of tags, querying the next tag path in turn, and determining whether there is a blank position; when there is a blank position, executing the step of determining that the blank position corresponds to the first index of the data table.

[0061] In addition, when the access is complete and there is no empty location, storage failure information is generated and returned.

[0062] In this embodiment, after the access is complete, if no empty location is found, a storage failure message needs to be generated and returned to the designated device to prompt the user that the storage failed. The designated device refers to the device that initiates the storage data request, which can be a mobile phone, a tablet computer, or a server.

[0063] Step S105: determining a first address of the data table based on the first index and the data table base address.

[0064] In this embodiment, the first index and the data table base address are added to obtain the first address of the data table.

[0065] Step S106, storing the data to be stored in the data table according to the first address of the data table.

[0066] After the data to be stored is stored in the data table, there may be a situation where the stored data needs to be queried or deleted. The following two situations are introduced.

[0067] The first one is to query the stored data.

[0068] In this embodiment, the cache parameter table is queried by the table number of the user parameter table to obtain the number of tags, the tag table base address and the data table base address corresponding to the user parameter table, and then the tag path table is queried based on the table number of the user parameter table to obtain the tag path entry number corresponding to the user table.

[0069] Compare the table entry number in the user parameter table with the table entry number stored in the tag path corresponding to the tag path entry number, query the table entry number of the user parameter table in the table entry number stored in the tag table, and when the table entry number is found, determine the second address of the data table according to the storage location of each table entry number corresponding to the second index of the data table and the base address of the data table, and read data from the data table based on the second address.

[0070] Specifically, after storing the data to be stored in the data table according to the address of the data table, it also includes: comparing the table item entry number with the table item entry number stored in the tag path corresponding to the tag path entry number, and when the table item entry number exists in the stored table item entry number, determining that the storage location of the table item entry number corresponds to the second index of the data table; determining the second address of the data table according to the second index and the data table base address; and reading data from the data table based on the second address of the data table.

[0071] In the case where the table entry number is not found, the tag path is traversed to query the table entry number. Specifically, in the case where the table entry number does not exist in the table entry number stored in the tag table, the method further includes: traversing the tag path in the tag table; and in the case where it is determined that the table entry number is found, executing the step of determining that the storage location of the table entry number corresponds to the second index of the data table.

[0072] In addition, when the entry number of the queried table item is not determined, query failure information is generated and returned.

[0073] In this embodiment, if the table entry number is not found, a query failure message needs to be generated and returned to the designated device to prompt the user that the query failed. At this time, the designated device refers to the device that initiates the query data request, which can be a mobile phone, a tablet computer or a server.

[0074] The second method is to delete the stored data.

[0075] In this embodiment, the cache parameter table is queried by the table number of the user parameter table to obtain the number of tags, the tag table base address and the data table base address corresponding to the user parameter table, and then the tag path table is queried based on the table number of the user parameter table to obtain the tag path entry number corresponding to the user table.

[0076] Compare the table entry number in the user parameter table with the table entry number stored in the tag path corresponding to the tag path entry number, query the table entry number of the user parameter table from the table entry number stored in the tag table, and when the table entry number is found, set the valid flag of the corresponding data to 0 to delete the data.

[0077] Specifically, after storing the data to be stored in the data table according to the address of the data table, it also includes: comparing the table item entry number with the table item entry number stored in the tag path corresponding to the tag path entry number, and when the table item entry number exists in the stored table item entry number, determining that the valid flag corresponding to the table item entry number is set to 0, and deleting the data corresponding to the table item entry number.

[0078] In the case where the table entry number is not found, the marking path is traversed to query the table entry number. Specifically, in the case where the table entry number does not exist in the table entry number stored in the marking table, the method further includes: traversing the marking path in the marking table; in the case where it is determined that the table entry number is queried, executing the step of determining that the valid flag corresponding to the table entry number is set to 0, and deleting the data corresponding to the table entry number.

[0079] In addition, when the entry number of the table item is not determined, deletion failure information is generated and returned.

[0080] In this embodiment, if the entry number is not found, a query failure message needs to be generated and returned to the designated device to prompt the user that the deletion failed. At this time, the designated device refers to the device that initiates the data deletion request, which can be a mobile phone, a tablet computer or a server.

[0081] The cache implementation method of the variable-length data block provided in the present embodiment queries the cache parameter table through the table number of the user parameter table to obtain the number of tags, the tag table base address and the data table base address corresponding to the user parameter table; the number of tags is used to indicate the size of the user parameter table; the cache parameter table also includes the data length of the data to be stored corresponding to the user parameter table; based on the table number of the user parameter table, the tag path table is queried to obtain the tag path entry number corresponding to the user table; based on the tag path entry number and the tag table base address, the tag table address is obtained; based on the tag table address, the tag table is accessed, and when there is a blank position in the tag path corresponding to the tag path entry number, it is determined that the blank position corresponds to the data table The method comprises the following steps: determining the first address of the data table based on the first index and the data table base address; storing the data to be stored in the data table according to the first address of the data table; solving the problem that if the length of each data read is set to be the same, the capacity of the cache will be wasted when the data block read is small; classifying the data in the form of a user parameter table structure, configuring the attributes of each user parameter table, controlling the size of the user parameter table by configuring tag_num, and controlling the length of the data by configuring data_len, the length of the data in the cache can be made variable, thereby avoiding wasting the capacity of the cache and improving the space utilization of the cache; and at the same time, improving the query efficiency to the memory.

[0082] Furthermore, by implementing three-level address mapping through the data table base address or tag table base address, entry number and index, it is possible to provide accuracy query of data query.

[0083] Corresponding to the above method, the present invention also provides a cache implementation device for variable-length data blocks, which includes a computer device, the computer device includes a processor and a memory, the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the device implements the steps of the cache implementation method for variable-length data blocks as mentioned above.

[0084] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the aforementioned variable-length data block cache implementation method are implemented. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a cache, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0085] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0086] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0087] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with or replace features of other embodiments.

[0088] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for implementing a cache of a variable-length data block, characterized in that: The method comprises: Based on the table number of the user parameter table, query the cache parameter table to obtain the number of tags, the tag table base address and the data table base address corresponding to the user parameter table; the number of tags is used to indicate the size of the user parameter table; the cache parameter table also includes the data length of the data to be stored corresponding to the user parameter table; Based on the table number of the user parameter table, query the tag path table to obtain the tag path entry number corresponding to the user parameter table; Based on the tag path entry number and the tag table base address, obtain a tag table address; accessing the tag table based on the tag table address, and determining, if there is a blank position in the tag path corresponding to the tag path entry number, that the blank position corresponds to a first index of the data table; Determine a first address of the data table based on the first index and the data table base address; According to the first address of the data table, the data to be stored is stored in the data table.

2. The method for implementing the cache of variable-length data blocks according to claim 1, characterized in that: In the case where there is no blank position in the marking path corresponding to the marking path entry number, the method further includes: According to the number of marks, access the mark table, query the next mark path in sequence, and determine whether there is a blank position; In the case that there is a blank position, the step of determining that the blank position corresponds to a first index of the data table is performed.

3. The method for implementing the cache of variable-length data blocks according to claim 2, characterized in that: If the access is complete and there is no empty location, a storage failure message is generated and returned.

4. The method for implementing the cache of variable-length data blocks according to claim 1, characterized in that: After determining that the blank position corresponds to the first index of the data table, the method further includes: storing the table number corresponding to the user parameter table, the table item number of each entry in the user parameter table and the valid identifier of the user parameter table in the tag table.

5. The method for implementing the cache of variable-length data blocks according to claim 4, characterized in that: After storing the data to be stored in the data table according to the address of the data table, the method further includes: comparing the table entry number with a table entry number stored in the tag path corresponding to the tag path entry number, and determining that a storage location of the table entry number corresponds to a second index of the data table when the table entry number exists in the stored table entry numbers; Determine a second address of the data table according to the second index and the data table base address; Based on the second address of the data table, data is read from the data table.

6. The method for implementing the cache of variable-length data blocks according to claim 5, characterized in that: In a case where the entry number does not exist in the entry numbers stored in the tag table, the method further includes: Traversing the tag path in the tag table; In the case where it is determined that the table entry number is found by querying, the step of determining that the storage location of the table entry number corresponds to the second index of the data table is performed.

7. The method for implementing the cache of variable-length data blocks according to claim 6, characterized in that: If the entry number of the table item is not determined by the query, query failure information is generated and returned.

8. The method for implementing the cache of variable-length data blocks according to claim 4, characterized in that: After storing the data to be stored in the data table according to the address of the data table, the method further includes: The table entry number is compared with the table entry number stored in the mark path corresponding to the mark path entry number. If the table entry number exists in the stored table entry number, the valid flag corresponding to the table entry number is determined to be set to 0, and the data corresponding to the table entry number is deleted.

9. A variable-length data block cache implementation device, comprising a processor and a memory, characterized in that: The memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the device implements the steps of the variable-length data block cache implementation method as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the variable-length data block cache implementation method as claimed in any one of claims 1 to 8 are implemented.

Images