Method and device for processing virtual address request
By introducing anti-backpression queues to process virtual address requests in the chip design, the problem of frequent backpressure upstream of memory management units is solved, system performance and cache line usage efficiency are improved, and the cost increase caused by increasing the number of cache group channels is avoided.
Patent Information
- Application Number
- CN202411253179.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-06
AI Technical Summary
In chip design, the memory management unit corresponds to the frequent backpressure upstream of multiple data origins leads to performance problems, increasing the number of cache groupings to solve this problem will significantly increase the chip area and cost.
Use anti-backpression queue to process virtual address requests, determine group information through address hashing, and perform address hit tests. If the hit is missing and no cache line is available, the request is written to the anti-backpression queue to wait, improving the efficiency of cache line usage and reduce the back pressure frequency.
The anti-backpression queue solves the upstream backpressure problem caused by virtual address requests, improves the overall performance of the system, reduces the backpressure frequency and improves the efficiency of cache lines.
Smart Images

Figure CN118760621B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computers, and in particular to a processing method and device based on virtual address requests. Background Art
[0002] Memory Management Unit (MMU) is usually used in computers or servers. It allows computers / servers to use more storage space than the actual physical memory through virtual memory. At the same time, the memory management unit also divides and protects the actual physical memory so that each software task can only access the memory space allocated to it. If a task attempts to access the memory space of other tasks, the memory management unit will automatically generate an exception to protect the programs and data of other tasks from being damaged.
[0003] The MMU is located between the processor core and the bus that connects the cache and physical memory. When the processor core fetches instructions or accesses data, it provides an effective address, also known as a logical address or virtual address. This address is generated by the linker when the executable code is compiled. The effective address does not need to match the actual hardware physical address of the system, but the MMU maps the effective address to the corresponding physical address to access instructions and data.
[0004] In general, when the memory management unit does a page table query, it will first look for the same virtual address item in the local cache. If there is an identical virtual address item, it is considered a hit. At this time, if the data is ready, it can be returned directly; otherwise, it is considered lost and a read request needs to be initiated to the memory. When the cache is large, it will be divided into sets and ways. Generally, there will be multiple ways in a group. When a virtual address request is input, a group information is first generated by address hashing, and then it is searched in the multi-way cache lines in this group. When the request is lost, it will look in this group to see if there is an available cache line at this time. If so, the cache line will be allocated; if not, it will wait until there is an available cache line in the group, at which time back pressure is required upstream.
[0005] It should be noted that the above introduction to the technical background is only for the convenience of providing a clear and complete description of the technical solutions of the present application and for the convenience of understanding by those skilled in the art. It cannot be considered that the above technical solutions are well known to those skilled in the art simply because they are described in the background technology section of the present application. Summary of the invention
[0006] The inventors found that in general chip design, a memory management unit will correspond to multiple data sources, and frequent upstream back pressure will cause performance problems. The usual solution to this problem is to increase the number of ways in each group of caches, but for the scenario of local group back pressure in local time, this solution will significantly increase the chip area and increase the cost.
[0007] In response to at least one of the above problems or other similar problems, an embodiment of the present application provides a method and device for processing virtual address requests, which solves the problem of upstream back pressure caused by a large number of virtual address requests through an anti-back pressure queue, improves the utilization efficiency of cache lines, reduces the frequency of back pressure, and improves the overall performance of the system.
[0008] According to one aspect of an embodiment of the present application, a method for processing a virtual address request is provided, the method comprising:
[0009] Performing address hashing on the received virtual address request to determine group information corresponding to the virtual address request;
[0010] Performing an address hit test in the group corresponding to the group information;
[0011] When the measurement result of the address hit test is a loss and there is no available cache line, the virtual address request is written into an anti-backpressure queue for waiting.
[0012] According to another aspect of an embodiment of the present application, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the aforementioned embodiment when executing the computer program.
[0013] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the aforementioned embodiments is implemented.
[0014] According to another aspect of an embodiment of the present application, a device for processing a virtual address request is provided, the device comprising:
[0015] A first processing unit, which performs address hashing on the received virtual address request to determine group information corresponding to the virtual address request;
[0016] A testing unit, which performs an address hit test in the group corresponding to the group information;
[0017] The second processing unit writes the virtual address request into an anti-backpressure queue for waiting when the measurement result of the address hit test is loss and there is no available cache line.
[0018] The beneficial effect of the embodiment of the present application is that: according to the embodiment of the present application, an anti-backpressure queue is used to solve the problem of backpressure upstream caused by a large number of virtual address requests, thereby improving the utilization efficiency of cache lines, reducing the backpressure frequency, and improving the overall system performance.
[0019] With reference to the following description and accompanying drawings, the specific embodiments of the present application are disclosed in detail, indicating the way in which the principles of the present application can be adopted. It should be understood that the embodiments of the present application are not limited in scope. Within the scope of the terms of the appended claims, the embodiments of the present application include many changes, modifications and equivalents.
[0020] Features described and / or illustrated with respect to one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.
[0021] It should be emphasized that the term “include / comprises” when used herein refers to the presence of features, integers, steps or components, but does not exclude the presence or addition of one or more other features, integers, steps or components. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:
[0023] Figure 1 is a schematic diagram of a method for processing a virtual address request according to an embodiment of the present application;
[0024] Figure 2 is a schematic diagram of a processing process of a virtual address request according to a method of an embodiment of the present application;
[0025] Figure 3 is a schematic diagram of a processing flow of a virtual address request according to a method of an embodiment of the present application;
[0026] Figure 4 It is a schematic diagram of a virtual address request processing device according to an embodiment of the present application. DETAILED DESCRIPTION
[0027] With reference to the accompanying drawings, the above and other features of the present application will become apparent through the following description. In the description and the accompanying drawings, specific embodiments of the present application are specifically disclosed, which show some embodiments in which the principles of the present application can be adopted. It should be understood that the present application is not limited to the described embodiments. On the contrary, the present application includes all modifications, variations and equivalents falling within the scope of the attached claims.
[0028] In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish different elements in terms of title, but do not indicate the spatial arrangement or temporal order of these elements, etc., and these elements should not be limited by these terms. The term "and / or" includes any one and all combinations of one or more of the associated listed terms. The terms "comprising", "including", "having", etc. refer to the presence of the stated features, elements, components or components, but do not exclude the presence or addition of one or more other features, elements, components or components.
[0029] In the embodiments of the present application, the singular forms "a", "the", etc. include plural forms and should be broadly understood as "a kind" or "a type" rather than being limited to the meaning of "one"; in addition, the term "said" should be understood to include both singular and plural forms, unless the context clearly indicates otherwise. In addition, the term "according to" should be understood as "at least in part according to...", and the term "based on" should be understood as "at least in part based on...", unless the context clearly indicates otherwise.
[0030] Various implementations of the present application are described below in conjunction with the accompanying drawings. These implementations are merely exemplary and are not intended to limit the present application.
[0031] Embodiments of the first aspect
[0032] An embodiment of the present application provides a method for processing a virtual address request.
[0033] Figure 1 FIG. 1 is a schematic diagram of a method for processing a virtual address request according to an embodiment of the present application. Figure 1 As shown, the method for processing the virtual address request includes:
[0034] 110: performing address hashing on the received virtual address request to determine group information corresponding to the virtual address request;
[0035] 120: Perform an address hit test in the group corresponding to the above group information;
[0036] 130 : When the measurement result of the address hit test is a loss and there is no available cache line, write the virtual address request into an anti-backpressure queue for waiting.
[0037] It is worth noting that the above Figure 1 The embodiments of the present application are only schematically described, but the present application is not limited thereto. For example, the execution order of the various operations can be appropriately adjusted, and other operations can be added or some operations can be reduced. Those skilled in the art can make appropriate modifications based on the above content, and are not limited to the above appended Figure 1 Records of.
[0038] According to the embodiment of the present application, an anti-backpressure queue is used to solve the problem of backpressure upstream caused by a large number of virtual address requests, thereby improving the utilization efficiency of cache lines, reducing the backpressure frequency, and improving the overall performance of the system.
[0039] In an embodiment of the present application, there is no restriction on the depth of the anti-back-pressure queue, which can be determined by the specific scenario. For example, if the cache is often full, the depth of the anti-back-pressure queue can be set deeper to cache enough lost virtual address requests; otherwise, the depth of the anti-back-pressure queue can be set shallower. The present application is not limited to this, and the depth of the anti-back-pressure queue can also be determined based on other factors, such as cost and budget. Moreover, as a type of cache, the anti-back-pressure queue can be of fixed depth or variable depth. For example, cache bars can be added by hot-plugging as storage space for the anti-back-pressure queue to achieve a variable-depth anti-back-pressure queue, and so on.
[0040] In the embodiment of the present application, there is no restriction on the writing method of writing the above-mentioned virtual address request into the anti-back pressure queue. In some possible implementations, the writing queue can be written sequentially or in a disorderly manner. For example, the disorderly writing is to write the virtual address request in a disorderly manner into an idle position by polling, so that the input virtual address request can continue to perform the address hit test instead of directly back-pressing the upstream, thereby improving the system performance. Thus, the pressure on the upstream is reduced.
[0041] In the embodiment of the present application, if the measurement result of the above-mentioned address hit test is a hit, the subsequent operation of the cache line can be performed normally. The specific operation can refer to the relevant technology and the description is omitted here.
[0042] In the embodiment of the present application, if the measurement result of the above-mentioned address hit test is a loss, but there is an available cache line in the group corresponding to the virtual address request, a cache line can be allocated to the virtual address request and the address cache index can be updated. The specific operation can refer to the relevant technology and the description is omitted here. Therefore, in the next request of the virtual address request, its hit test result is "hit".
[0043] In the embodiment of the present application, after the virtual address request is written into the anti-backpressure queue, the position (or space) in the anti-backpressure queue where the virtual address request is written may be marked as busy, thereby preventing the position (or space) from being repeatedly occupied.
[0044] In an embodiment of the present application, a periodic judgment may be performed on the virtual address requests in the anti-back pressure queue, that is, it is determined whether the group corresponding to the virtual address request in the anti-back pressure queue has an available cache line. If so, the virtual address request can be read out from the anti-back pressure queue and the address hit test can be re-performed, that is, an address hit test can be further performed in the group corresponding to the virtual address request. If the measurement result of the address hit test is still lost, a cache line is allocated to the virtual address request.
[0045] In the above embodiment, there is no restriction on the timing of making the above judgment, and the above judgment can be made when the number of virtual address requests in the anti-backpressure queue reaches a certain level; the above judgment can also be made at intervals according to system settings; a timer can also be set, and the above judgment can be made when the timer expires; a counter can also be set, and the value of the counter is increased by 1 each time a virtual address request is written, and the above judgment can be made when the value of the counter reaches a preset threshold; the above judgment can also be made continuously in real time, and so on.
[0046] In the above embodiment, since the above virtual address request is a virtual address request in the anti-backpressure queue, the virtual address request has been subjected to an address hit test once, and therefore, the virtual address request may not be subjected to an address hit test again, that is, when the group corresponding to the virtual address request in the anti-backpressure queue has an available cache line, the cache line is directly allocated to the virtual address request. In this way, the processing speed can be further improved, thereby improving the system performance.
[0047] In the above embodiment, after the virtual address request is read out from the anti-backpressure queue, the position (or space) corresponding to the virtual address request in the anti-backpressure queue can also be marked as free. Thus, the freed address (or space) can be used to save other virtual address requests that have no hit in subsequent address hit tests and have no available cache lines.
[0048] In the above embodiment, optionally, for the virtual address request in the anti-backpressure queue, when it is determined that the group corresponding to the virtual address request in the anti-backpressure queue has an available cache line, an address hash may be performed to determine the group to which it corresponds, and subsequent processing may be performed when the results of the two address hashing processes are consistent. In this way, the accuracy of the query can be improved and system errors can be avoided.
[0049] In an embodiment of the present application, arbitration can be performed for newly received virtual address requests and virtual address requests in an anti-back pressure queue, and the above-mentioned hit test is performed on virtual address requests with higher priorities first. For example, the priority of virtual address requests in an anti-back pressure queue is pre-set to be higher than the priority of newly received virtual address requests, and virtual address requests in the anti-back pressure queue are processed first. The present application does not limit the method for setting the priority of newly received virtual address requests and the priority of virtual address requests in an anti-back pressure queue, and reference may be made to related technologies.
[0050] In the embodiment of the present application, for the above-mentioned anti-backpressure queue, a backpressure coefficient can also be set, that is, when the number of virtual address requests in the anti-backpressure queue reaches the number specified by the preset backpressure coefficient, backpressure upstream processing is performed. For example, in an anti-backpressure queue with a fixed depth, it can be set to perform backpressure upstream only when the anti-backpressure queue is full, or it can be set to perform backpressure upstream immediately as long as there is data in the anti-backpressure queue, or it can be set to perform backpressure upstream when the data in the anti-backpressure queue reaches a predetermined proportion of the total depth, etc., thereby meeting the needs of different application scenarios.
[0051] This application does not limit the processing method of the upstream back pressure, and you can refer to the relevant technology.
[0052] The above embodiments are merely exemplary of the embodiments of the present application, but the present application is not limited thereto, and appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.
[0053] Figure 2 It is a schematic diagram of the processing process of the virtual address request according to the method of the embodiment of the present application, showing the hardware circuit design of the memory management unit for the virtual address request.
[0054] like Figure 2 As shown, for a new virtual address request, an address hash 211 is first performed on it to determine its corresponding group information. The virtual address request passes through multiple pipelines and reaches the address hit test 212. In addition, the group information corresponding to the virtual address request is also passed to the address index cache 213. The address hit test 212 performs an address hit test in the group corresponding to the virtual address request. If it hits, subsequent processing is performed; if it is missed (miss), but there is an available cache line, a cache line 214 is allocated to it for subsequent processing; if it is missed (miss) and there is no available cache line, it is written to the anti-backpressure queue 215 to wait for subsequent processing.
[0055] In the above example, the processing of the virtual address request in the anti-backpressure queue 215 has been described in detail above and will not be repeated here.
[0056] Figure 3 It is a schematic diagram of the processing flow of a virtual address request according to the method of an embodiment of the present application.
[0057] like Figure 3 As shown, the method includes:
[0058] 310: A virtual address request is received (if it is a new virtual address request, the address hash can be performed to obtain the group information corresponding to the request);
[0059] 320: Perform an address hit test in the group corresponding to the above group information. If the measurement result is a hit, execute operation 330; if the measurement result is a miss, execute operation 340;
[0060] 330: perform subsequent processing of the cache line;
[0061] 340: Apply for a cache line and send the virtual address request to the memory. If there is an available cache line, perform operation 350. If there is no available cache line, perform operation 360.
[0062] 350: Allocate cache lines and update address index cache;
[0063] 360: Determine whether the predetermined time has passed, if the predetermined time has passed, execute operation 370, otherwise return to operation 310;
[0064] 370: Write the virtual address request to the anti-backpressure queue and mark the corresponding space as busy.
[0065] In operation 310, the virtual address request may be a new virtual address request, or a virtual address request in the anti-backpressure queue, or a virtual address request with a higher priority after arbitration. The specific arbitration method has been described above and will not be repeated here.
[0066] In operation 340, the requested cache line cannot be re-applied before the memory data is returned to avoid repeated occupation. After the data read from the memory is returned, the request that hits the corresponding cache line can be released.
[0067] In operation 370 , if virtual address requests of the same group are continuously received, and the hit test result is a miss, and there is no available cache line in the group, the virtual address request is written into the anti-backpressure queue, and the space in the anti-backpressure queue is marked as busy.
[0068] In operation 370, if the virtual address request is a virtual address request in the anti-back pressure queue, then if there is an available cache line in the group where the virtual address request is located, the virtual address request can be read out from the anti-back pressure queue, and this space in the anti-back pressure queue can be marked as free for other virtual address requests that have not hit and have no available cache lines.
[0069] In the above example, there is no limit on the predetermined time, which can be set as needed, and operation 360 is optional, and the virtual address request can also be directly written into the anti-backpressure queue when there is no hit and no available cache line.
[0070] It is worth noting that the above Figure 3 The embodiments of the present application are only schematically described, but the present application is not limited thereto. For example, the execution order of the various operations can be appropriately adjusted, and other operations can be added or some operations can be reduced. Those skilled in the art can make appropriate modifications based on the above content, and are not limited to the above appended Figure 3 Records of.
[0071] According to the embodiment of the present application, an anti-backpressure queue is used to solve the problem of upstream backpressure caused by a large number of requests, thereby improving the utilization efficiency of cache lines, reducing the frequency of backpressure, and improving the overall performance of the system.
[0072] Embodiments of the second aspect
[0073] The embodiment of the present application provides a device for processing a virtual address request. In the embodiment of the present application, the principle of solving the problem by the device for processing a virtual address request is the same as the method for processing a virtual address request in the embodiment of the first aspect, and the same contents will not be repeated.
[0074] Figure 4 is a schematic diagram of a processing device for a virtual address request according to an embodiment of the present application. Figure 4 As shown, the virtual address request processing device 400 of the embodiment of the present application includes:
[0075] A first processing unit 410 performs address hashing on the received virtual address request to determine group information corresponding to the virtual address request;
[0076] A testing unit 420, which performs an address hit test in the group corresponding to the above group information;
[0077] The second processing unit 430 writes the virtual address request into an anti-backpressure queue for waiting when the measurement result of the address hit test is a loss and there is no available cache line.
[0078] In some embodiments, when the measurement result of the address hit test is a miss and there is an available cache line, the second processing unit 430 allocates a cache line to the virtual address request and updates the address index cache.
[0079] In some embodiments, the second processing unit 430 writes the virtual address request into the anti-backpressure queue, including: sequential writing or disorderly writing.
[0080] In some embodiments, after writing the virtual address request into the anti-backpressure queue, the second processing unit 430 further marks the position in the anti-backpressure queue where the virtual address request is written as busy.
[0081] In some embodiments, Figure 4 As shown, the processing device 400 also includes:
[0082] The judgment unit 440 judges whether the group corresponding to the virtual address request in the above-mentioned anti-backpressure queue has an available cache line; if so, the first processing unit 410 reads the virtual address request from the anti-backpressure queue, and the test unit 420 performs an address hit test in the group corresponding to the virtual address request; the second processing unit 430 allocates a cache line for the virtual address request when the measurement result of the above-mentioned address hit test is a loss.
[0083] In the above embodiment, after allocating a cache line for the virtual address request, the second processing unit 430 may further mark the position corresponding to the virtual address request in the anti-backpressure queue as free.
[0084] In some embodiments, the first processing unit 410 further arbitrates the received virtual address request and the virtual address requests in the anti-backpressure queue; and the testing unit 420 performs the hit test on the virtual address request with a high priority.
[0085] In some embodiments, when the number of virtual address requests in the anti-backpressure queue reaches a number specified by a preset backpressure coefficient, the second processing unit 430 performs backpressure upstream processing.
[0086] The above embodiments are merely exemplary of the embodiments of the present application, but the present application is not limited thereto, and appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.
[0087] It is worth noting that the above only describes the components or modules related to the present application, but the present application is not limited thereto. The virtual address request processing device 400 of the present embodiment may also include other components or modules, and the specific contents of these components or modules may refer to the relevant technology.
[0088] Furthermore, for simplicity, Figure 4 The connection relationship or signal direction between the various components or modules is only exemplified, but it should be clear to those skilled in the art that various related technologies such as bus connection can be used. The above-mentioned various components or modules can be implemented by hardware facilities such as processors, memories, transmitters, receivers, etc.; the implementation of this application is not limited to this.
[0089] In the above embodiment, the processing device 400, as a general processing device, can also perform basic controls including but not limited to data handling, starting and / or stopping the computing device. In addition, according to different implementations, the processing device 400 can be a central processing unit (CPU), a graphics processing unit (GPU) or one or more types of processors in other general processors and / or special processors, including but not limited to digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., and their number can be determined according to actual needs. As mentioned above, only with respect to the computing device disclosed in the present invention, it can be regarded as having a single-core structure or a homogeneous multi-core structure. However, when the computing device and the processing device 400 are integrated and considered together, the two are regarded as forming a heterogeneous multi-core structure.
[0090] According to the embodiment of the present application, an anti-backpressure queue is used to solve the problem of upstream backpressure caused by a large number of requests, thereby improving the utilization efficiency of cache lines, reducing the frequency of backpressure, and improving the overall performance of the system.
[0091] An embodiment of the present application further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any one of the methods in the embodiment of the first aspect is implemented.
[0092] For example, the processor functions as the aforementioned processing device 400. The implementation of the processing device 400 has been described above, and its content is incorporated here and will not be repeated here.
[0093] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any one of the methods in the embodiments of the first aspect is implemented.
[0094] An embodiment of the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, any one of the methods in the embodiments of the first aspect is implemented.
[0095] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0096] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0097] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0099] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.
Claims
1. A method for processing a virtual address request, characterized in that: The method comprises: Performing address hashing on the received virtual address request to determine group information corresponding to the virtual address request; Performing an address hit test in the group corresponding to the group information; When the measurement result of the address hit test is a loss and there is no available cache line, the virtual address request is written into an anti-backpressure queue for waiting.
2. The method according to claim 1, characterized in that The method further comprises: In the case where the measurement result of the address hit test is a miss and there is an available cache line, a cache line is allocated to the virtual address request and the address index cache is updated.
3. The method according to claim 1, characterized in that Writing the virtual address request into an anti-backpressure queue includes: Sequential or out-of-order writing.
4. The method according to claim 1, characterized in that: After writing the virtual address request into the anti-backpressure queue, the method includes: The position in the anti-backpressure queue where the virtual address request is written is marked as busy.
5. The method according to claim 1, characterized in that The method further comprises: Determine whether a group corresponding to a virtual address request in the anti-backpressure queue has an available cache line; If yes, the virtual address request is read out from the anti-backpressure queue, and an address hit test is performed in the group corresponding to the virtual address request; In case the measurement result of the address hit test is a miss, a cache line is allocated for the virtual address request.
6. The method according to claim 5, characterized in that The method further comprises: The position corresponding to the virtual address request in the anti-backpressure queue is marked as idle.
7. The method according to claim 1, characterized in that The method further comprises: arbitrating the received virtual address request and the virtual address requests in the anti-backpressure queue; The hit test is performed on the virtual address request with a high priority.
8. The method according to claim 1, characterized in that: The method further comprises: When the number of virtual address requests in the anti-backpressure queue reaches the number specified by the preset backpressure coefficient, backpressure upstream processing is performed.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.
11. A virtual address request processing device, characterized in that: The device comprises: A first processing unit, which performs address hashing on the received virtual address request to determine group information corresponding to the virtual address request; A testing unit, which performs an address hit test in the group corresponding to the group information; The second processing unit writes the virtual address request into an anti-backpressure queue for waiting when the measurement result of the address hit test is loss and there is no available cache line.
Citation Information
Patent Citations
Data transmission and task processing method, device and equipment
CN111309649A
Message caching method, integrated circuit system and storage medium
CN114766090A
Cache processing method and device, electronic equipment and medium
CN117331854A
Memory management device and method, chip and electronic equipment
CN118193411A
Memory management unit and method, chip and electronic equipment
CN118312449A
