CN117632820A - Request processing method, device, bus bridge, electronic equipment and readable storage medium - Google Patents
Request processing method, device, bus bridge, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN117632820A CN117632820A CN202410090405.2A CN202410090405A CN117632820A CN 117632820 A CN117632820 A CN 117632820A CN 202410090405 A CN202410090405 A CN 202410090405A CN 117632820 A CN117632820 A CN 117632820A
- Authority
- CN
- China
- Prior art keywords
- request
- bus
- response data
- target
- reservation stack
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 27
- 230000004044 response Effects 0.000 claims abstract description 269
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 31
- 230000005540 biological transmission Effects 0.000 claims description 39
- 238000004891 communication Methods 0.000 claims description 22
- 238000006243 chemical reaction Methods 0.000 claims description 16
- 238000010586 diagram Methods 0.000 description 12
- 238000004590 computer program Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000002093 peripheral effect Effects 0.000 description 4
- 230000003068 static effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 3
- 230000008707 rearrangement Effects 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Bus Control (AREA)
Abstract
The embodiment of the invention provides a request processing method, a request processing device, a bus bridge, electronic equipment and a readable storage medium, and relates to the technical field of computers, wherein the method comprises the following steps: in response to receiving a first request sent by a first bus, storing the first request in a preset reservation stack; converting the first request in the reservation stack into a second request conforming to the second bus, and sending the second request in the reservation stack to the second bus; in response to receiving the response data sent by the second bus, converting the response data into response data conforming to the first bus as target response data, and storing the target response data in the reservation stack; and sending the target response data in the reserved stack to the first bus according to the designated response sequence of the first bus. Compared with the method for sending the next request after the response data of the previous request is returned in the prior art, the request processing method provided by the embodiment of the invention improves the efficiency of request processing.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and apparatus for processing a request, a bus bridge, an electronic device, and a readable storage medium.
Background
With the development of computer technology, each device can perform data transmission through an on-chip bus, and when devices adopting different buses communicate with each other, requests and responses between different devices need to be realized through protocol conversion.
Currently, in order to ensure data consistency, a part of bus protocol often specifies the return sequence of response data. However, since the response time of the device executing the processing operation is different for each request, the return sequence of the response data cannot be guaranteed to be consistent with the return sequence specified by the bus, so that the current mode is to send the next request after the response data of the previous request is returned, which results in blocking of the request transmission and greatly reduces the efficiency of the request processing.
Disclosure of Invention
The embodiment of the invention provides a request processing method, a request processing device, a bus bridge, electronic equipment and a readable storage medium, which can solve the problem of low request processing efficiency in the prior art.
In order to solve the above problems, an embodiment of the present invention discloses a request processing method, which includes:
In response to receiving a first request sent by a first bus, storing the first request in a preset reservation stack;
converting the first request in the reservation stack into a second request conforming to a second bus, and sending the second request in the reservation stack to the second bus;
in response to receiving response data sent by the second bus, converting the response data into response data conforming to the first bus as target response data, and storing the target response data in the reservation stack;
and sending the target response data in the reservation stack to the first bus according to the designated response sequence of the first bus.
Optionally, the reservation stack includes a first reservation stack and a second reservation stack; the storing the first request in a preset reservation stack includes:
acquiring a request type of the first request;
determining a first target reservation stack from the first reservation stack and the second reservation stack based on the request type;
storing the first request in the first target reservation stack;
the storing the target response data in the reservation stack includes:
Acquiring a response type of the target response data;
determining a second target reservation stack from the first reservation stack and the second reservation stack based on the response type;
and storing the target response data into the second target reservation stack.
Optionally, after the converting the first request in the reservation stack to the second request conforming to the second bus, the method further includes:
generating a target identifier based on the request identifier of the first request, the request type of the first request and the stored index value of the first request in the reservation stack, and taking the target identifier as the request identifier of the second request;
the storing the target response data in the reservation stack includes:
determining a storage index value of a first request corresponding to the target response data in the reservation stack based on the response identification of the target response data;
and storing the target response data to a storage address indicated by the storage index value.
Optionally, the storing the first request in the first target-reservation stack includes:
dividing the first request into a plurality of sub-requests;
storing the plurality of sub-requests into the first target reservation stack in a single bit transmission manner;
The storing the target response data in the second target reservation stack includes:
dividing the target response data into a plurality of sub-responses;
and storing the plurality of sub-responses into the second target reservation stack in a single bit transmission mode.
Optionally, the sending the target response data in the reservation stack to the first bus according to the specified response sequence of the first bus includes:
selecting a plurality of sub-responses from the second target reservation stack according to the appointed response sequence of the first bus, and taking the sub-responses as sub-responses to be sent;
and splicing the sub-responses to be sent to obtain responses to be sent, and sending the responses to be sent to the first bus.
Optionally, the first bus is an AXI bus, and the second bus is a TileLink bus.
On the other hand, the embodiment of the invention discloses a bus bridge which is respectively connected with first equipment and second equipment; the first device adopts a first bus, and the second device adopts a second bus; the bus bridge is used for executing the request processing method.
In another aspect, an embodiment of the present invention discloses a request processing apparatus, including:
The first storage module is used for responding to the received first request sent by the first bus and storing the first request into a preset reservation stack;
the first conversion module is used for converting the first request in the reservation stack into a second request conforming to a second bus and sending the second request in the reservation stack to the second bus;
the second conversion module is used for responding to the received response data sent by the second bus, converting the response data into response data conforming to the first bus, taking the response data as target response data, and storing the target response data into the reservation stack;
and the sending module is used for sending the target response data in the reservation stack to the first bus according to the designated response sequence of the first bus.
Optionally, the reservation stack includes a first reservation stack and a second reservation stack; the first memory module includes:
the first acquisition sub-module is used for acquiring the request type of the first request;
a first determination submodule, configured to determine a first target reservation stack from the first reservation stack and the second reservation stack based on the request type;
A second storage sub-module configured to store the first request in the first target reservation stack;
the second conversion module includes:
the second acquisition sub-module is used for acquiring the response type of the target response data;
a second determination submodule, configured to determine a second target reservation stack from the first reservation stack and the second reservation stack based on the response type;
and the third storage sub-module is used for storing the target response data into the second target reservation stack.
In still another aspect, the embodiment of the invention also discloses an electronic device, which comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus; the memory is used for storing executable instructions which enable the processor to execute the request processing method.
The embodiment of the invention also discloses a readable storage medium, which enables the electronic equipment to execute the request processing method when the instructions in the readable storage medium are executed by the processor of the electronic equipment.
The embodiment of the invention also discloses a computer program product containing instructions, which when run on a computer, cause the computer to execute the request processing method.
The embodiment of the invention has the following advantages:
the embodiment of the invention provides a request processing method, which is characterized in that a first request sent by a first bus is received, and the first request is stored in a preset reservation stack; converting the first request in the reservation stack into a second request conforming to a second bus, and sending the second request in the reservation stack to the second bus; in response to receiving response data sent by the second bus, converting the response data into response data conforming to the first bus as target response data, and storing the target response data in the reservation stack; and sending the target response data in the reservation stack to the first bus according to the designated response sequence of the first bus. Compared with the method that the next request is sent after the response sequence of the previous request is returned in the prior art, the request processing method provided by the embodiment of the invention can temporarily store the request and the response data by using the reservation stack through setting the reservation stack, and can realize rearrangement of the target response data in the reservation stack by sending the target response data in the reservation stack according to the appointed response sequence of the first bus, so that the return sequence of the response data is consistent with the appointed response sequence of the first bus, the next request is not required to be sent after the response data of the previous request is returned, the request transmission is prevented from being blocked, and the request processing efficiency is improved. The system bandwidth utilization rate is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of an embodiment of a request processing method of the present invention;
FIG. 2 is a block diagram of the structure of a bus bridge of the present invention;
FIG. 3 is a block diagram of an embodiment of a request processing apparatus of the present invention;
fig. 4 is a block diagram of an electronic device for request processing according to an example of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present invention may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type, and are not limited to the number of objects, such as the first object may be one or more. Furthermore, the term "and/or" as used in the specification and claims to describe an association of associated objects means that there may be three relationships, e.g., a and/or B, may mean: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. The term "plurality" in embodiments of the present invention means two or more, and other adjectives are similar.
Method embodiment
Referring to fig. 1, there is shown a flowchart of steps of an embodiment of a request processing method of the present invention, the method may specifically include the steps of:
Step 101, in response to receiving a first request sent by a first bus, storing the first request in a preset reservation stack.
Step 102, converting the first request in the reservation stack into a second request conforming to a second bus, and sending the second request in the reservation stack to the second bus.
Step 103, in response to receiving the response data sent by the second bus, converting the response data into response data conforming to the first bus, as target response data, and storing the target response data in the reservation stack.
And 104, transmitting the target response data in the reservation stack to the first bus according to the designated response sequence of the first bus.
It should be noted that, for the steps 101 to 104, the bus in the embodiment of the present invention refers to a bus protocol, which defines a communication rule for transmitting data or signals, and different devices may use different bus protocols. The first bus may be AMBA (Advanced Microcontroller Bus Architecture) 3.0.0 bus protocol (Advanced eXtensible Interface, AXI) proposed by ARM corporation, which is widely used for high speed interconnects and peripherals. The second bus may be a bus-on-chip (TL) suitable for an open source reduced instruction set (RISC-V) processor, and may be any other bus protocol, which is not limited by the embodiment of the present invention. The embodiment of the invention can be applied to a system comprising a plurality of connected devices, and the interconnected devices can adopt different buses.
The first request may be sent by a device that uses the first bus, and may be a data read request or a data write request. The reservation stack may be pre-constructed, a static random access memory (Static Random Access Memory, SRAM) may be used, and a plurality of SRAMs may be used to form a memory bank as the reservation stack. Alternatively, the register set may be used to construct the reservation stack, so as to improve the efficiency of data reading and writing in the reservation stack.
Specifically, in the embodiment of the present invention, when a first request sent by a first bus is received, the first request may be temporarily stored in a reservation stack at this time, and the first request in the reservation stack may be converted into a second request conforming to a second bus. Specifically, the conversion operation may be performing address and request state conversion according to the protocol rules of the first bus and the second bus, that is, resolving the first request according to the protocol rules of the first bus to obtain a request address and a request state of the first request, and recombining the request address and the request state according to the protocol rules of the second bus to generate a second request conforming to the second bus.
The sending operation may be performed when the number of the second requests stored in the reservation stack reaches the storage threshold, or may be sent immediately after the first request is converted into the second request, which is not limited in the embodiment of the present invention. The sending operation may be sending in a first-in-first-out order, that is, sending the second request corresponding to the first request stored in the reservation stack first, and sending the second request corresponding to the first request stored in the reservation stack later. Alternatively, the transmission may be performed simultaneously, or may be performed in order of first-in and last-out, and specifically may be set according to a rule of the first bus, which is not limited in the embodiment of the present invention.
The sending to the second bus refers to sending to a device using the second bus, which may be a processor, or may be another processing device, or may be a device connected to a device that sends the first request.
Further, after receiving the response data returned by the second bus, the response data may be converted into target response data conforming to the first bus, and the target response data may be stored in the reservation stack. Specifically, the conversion operation may be to parse the response data according to the protocol rule of the second bus to obtain a response type, a response state, data, and the like, and reorganize the response type, the response state, the data, and the like according to the protocol rule of the first bus to generate the target response data conforming to the first bus.
Further, the specified response sequence is defined by the first bus, which defines the return sequence of response data between requests of different identities and different types. Illustratively, taking the first bus as an AXI bus as an example, the above specified response sequence may be: response data of read requests having the same identification must be returned in the transmission order, and response data of write requests having the same identification must be returned in the transmission order. Therefore, according to the embodiment of the invention, according to the sending sequence of the second request corresponding to the target response data in the reservation stack, each target response data can be sequentially sent to the first bus according to the return sequence specified by the first bus.
Taking the first bus as AXI and the second bus as TL as an example, the bus bridge design of TileLink and AXI4 widely used at present uses a blocking pipeline form, and the inter-protocol conversion uses a forwarding form, that is, the information of AXI4 channels is directly converted into the corresponding information of TileLink channels. In order to meet the forwarding between different bus protocols, a plurality of sub-modules need to be designed. The method comprises matching transmission capacity, dividing multi-bit transmission into single-bit transmission, storing user signals, and converting protocol signals. Pipelining results in higher conversion efficiency while improving bandwidth utilization of the processor system. But the characteristics of the AXI4 protocol can cause blocking problems for such a forward pipeline transmission. The AXI4 protocol specifies that there are no sequential requirements for reading transactions of different identities (Identity document, ID) of the response independent of each other, but that responses of the same ID transaction do not allow for interleaving, and that responses must be returned strictly in the order of the requests. In the prior art, requests with the same ID need to wait for the response of the previous requests with the same ID to be returned, and in extreme cases, if all requests with the same ID are used by AXI, the whole pipeline is equivalent to serial processing, and only one AXI transaction exists in the whole system, so that the utilization rate of the system bandwidth is seriously reduced.
Compared with the method that the next request is sent after the response sequence of the previous request is returned in the prior art, the request processing method provided by the embodiment of the invention can temporarily store the request and the response data by using the reservation stack through setting the reservation stack, and can realize rearrangement of the target response data in the reservation stack by sending the target response data in the reservation stack according to the appointed response sequence of the first bus, so that the return sequence of the response data is consistent with the appointed response sequence of the first bus, the next request is not required to be sent after the response data of the previous request is returned, the request transmission is prevented from being blocked, and the request processing efficiency is improved. The system bandwidth utilization rate is improved.
In an optional embodiment of the present invention, the reservation stack includes a first reservation stack and a second reservation stack, and the storing the first request in the preset reservation stack in step 101 may specifically include the following steps:
a substep 1011 of obtaining a request type of the first request;
substep 1012, determining a first target reservation stack from the first reservation stack and the second reservation stack based on the request type.
Substep 1013, storing the first request in the first target reservation stack.
The storing the target response data in the reservation stack in step 103 may specifically include the following steps:
a substep 1031 of obtaining a response type of the target response data;
substep 1032, determining a second target reservation stack from the first reservation stack and the second reservation stack based on the response type.
Substep 1033, storing the target response data in the second target reservation stack.
The first reservation stack and the second reservation stack may correspond to different request types and response types, where the request types may include a read operation and a write operation, and the response types may include a read data and a write reply. For example, a first reservation stack may be made to correspond to a read operation and read data, and a second reservation stack may be made to correspond to a write operation and write reply. Specifically, the request type may be obtained through an operation code of the first request, specifically, the first request may be parsed according to the specification of the first bus, the data of the operation code field of the first request may be obtained, and the operation type corresponding to the data may be determined as the request type of the first request. Accordingly, the response type may be obtained through the opcode field of the target response data.
Further, the embodiment of the invention can determine the first target reservation stack corresponding to the request type according to the request type of the first request, and store the first request into the corresponding first target reservation stack. Accordingly, the target response data is stored in a second target reservation stack corresponding to the response type.
In the embodiment of the invention, the reservation stack comprises a first reservation stack and a second reservation stack, and the request type of the first request can be acquired; determining a first target reservation stack from the first reservation stack and the second reservation stack based on the request type; storing the first request in the first target reservation stack; acquiring a response type of the target response data; determining a second target reservation stack from the first reservation stack and the second reservation stack based on the response type; and storing the target response data into the second target reservation stack. Therefore, the request/response data with different request types and different response types can be stored respectively, the mutually independent state control is realized, and the accurate management of the request transmission and the response data transmission is further improved.
Optionally, after the above operation of converting the first request in the reservation stack to the second request conforming to the second bus, the embodiment of the present invention may specifically further include the following steps:
S11, generating a target identifier based on the request identifier of the first request, the request type of the first request and the storage index value of the first request in the reservation stack, and taking the target identifier as the request identifier of the second request.
The above operation of storing the target response data in the reservation stack may specifically include the following steps:
s12, determining a storage index value of the first request corresponding to the target response data in the reservation stack based on the response identification of the target response data.
And S13, storing the target response data to a storage address indicated by the storage index value.
Specifically, for the steps S11 to S13, the request identifier refers to the ID of the first request, which is generated by the device that issues the first request, and may be obtained through the identifier field of the first request. The storage index value may characterize a storage address of the first request in the reservation stack. In the case where the reservation stack is made up of a plurality of SRAMs, the storage index value may be an identification of the SRAM in which the first request is located.
The type sub-identifier may be generated for the request type of the first request, for example, the type sub-identifier corresponding to the read request is 1, and the type sub-identifier corresponding to the write request is 0. Of course, other ways may be used, and embodiments of the invention are not limited in this regard.
Further, the request identifier of the first request, the type sub-identifier and the stored index value may be spliced to generate the target identifier. Illustratively, the target identification may be:
sourceID = isR+entryID+AXIID
wherein, sourceID characterizes the target identifier, isR characterizes the type sub-identifier, if the read request is 1, it is not 0. The entid indicates that the AXI request is stored in the index of the reservation stack, i.e., the stored index value described above. AXIID represents the AXI request ID, i.e. the request identification of the first request.
Further, after the device adopting the second bus responds to the second request, a response identifier is generated for the response data, where the response identifier is generally consistent with the request identifier of the second request, so that in the embodiment of the invention, the response identifier of the target response data is consistent with the request identifier sourceID of the corresponding second request.
Optionally, after generating the target identifier, the embodiment of the invention may further use a register set to create an ID mapping relationship, and map the request identifier of the first request with the target identifier of the second request.
In the embodiment of the invention, a target identifier is generated based on the request identifier of the first request, the request type of the first request and the storage index value of the first request in the reservation stack, and the target identifier is used as the request identifier of the second request; determining a storage index value of a first request corresponding to the target response data in the reservation stack based on the response identification of the target response data; and storing the target response data to a storage address indicated by the storage index value. Thus, by generating the target identifier for the second request, the first request with the same request identifier can be distinguished, so that the target response data can be quickly corresponding to the first request through the target identifier, and by storing the target response data to the storage address indicated by the storage index value, the response data corresponding to the first request with the same identifier can be quickly distinguished, and the request processing efficiency can be further improved.
Optionally, the above operation of storing the first request in the first target reservation stack may specifically include the following steps:
s21, dividing the first request into a plurality of sub-requests.
S22, storing the plurality of sub-requests into the first target reservation stack in a single-bit transmission mode.
The dividing operation may be to decompose the second request according to a preset target size, and a "last" flag may be set at the boundary, so as to distinguish different sub-requests through the last flag.
The single-bit transmission refers to one transaction transmission, only one data transmission is performed, so that the data transmission amount of the transaction is smaller than or equal to the bus width, and the multi-bit transmission refers to multiple data transmissions in one transaction transmission, that is, the data transmission amount of the transaction is larger than the bus width. Further, in the single-bit transmission mode, the same first request can be ensured to be correspondingly stored in each sub-storage area (item) in the reserved stack to a certain extent, so that the first request can be more conveniently converted into a second request, and the conversion efficiency is improved.
Accordingly, after the target response data is obtained, the target response data can be stored in the second target reservation stack in a splitting and single-bit transmission mode, so that the storage efficiency is improved.
Alternatively, in the case where the request type of the first request is a write request, the write request may also be expanded to the next power of 2 size. It is also possible to set a target size for it, and to execute the request expansion operation again in the case where the next power of 2 is not larger than the target size.
Optionally, the foregoing operation of sending the target response data in the reservation stack to the first bus according to the specified response sequence of the first bus may specifically include:
s31, selecting a plurality of sub-responses from the second target reservation stack according to the designated response sequence of the first bus, and taking the sub-responses as sub-responses to be sent.
S32, splicing the sub-responses to be sent to obtain responses to be sent, and sending the responses to be sent to the first bus.
Further, since the target response data is divided, before the target response data is sent to the first bus, it is necessary to convert the sub-responses into correct responses, that is, splice sub-responses belonging to the same target response data.
Specifically, the sub-responses to be sent may be a sourceID of a response to be sent currently determined according to a specified response sequence of the first bus, and a plurality of sub-responses corresponding to the sourceID are selected from all sub-responses contained in the reservation stack as the sub-responses to be sent.
Specifically, the splicing operation may be to splice according to the format according to the response data format of the first bus, and after splicing, the "last" flag existing in the first bus may be deleted. Alternatively, for writing requested response data, a "valid" flag on the injected segment of response data may also be cleared, where the "valid" flag is used to characterize the validity of the response data, and may be cleared in order to reduce the amount of data transferred.
Optionally, the first bus is an AXI bus, and the second bus is a TileLink bus.
Among other things, AXI buses are widely used for high-speed interconnects and peripherals. The TileLink bus is widely used in processors as an on-chip bus for RISC-V processor architecture. On this basis, in order to allow the RISC-V processor to flexibly adapt to more existing AXI devices (IP resources), the requests sent from the AXI bus to the TileLink bus need to be processed.
The embodiment of the invention provides a request processing method, which is characterized in that a first request sent by a first bus is received, and the first request is stored in a preset reservation stack; converting the first request in the reservation stack into a second request conforming to a second bus, and sending the second request in the reservation stack to the second bus; in response to receiving response data sent by the second bus, converting the response data into response data conforming to the first bus as target response data, and storing the target response data in the reservation stack; and sending the target response data in the reservation stack to the first bus according to the designated response sequence of the first bus. Compared with the method that the next request is sent after the response data of the previous request is returned in the prior art, the request processing method provided by the embodiment of the invention has the advantages that the reservation stack is arranged, the request and the response data can be temporarily stored by using the reservation stack, the target response data in the reservation stack can be rearranged in the reservation stack by sending the target response data according to the designated response sequence of the first bus, so that the return sequence of the response data is consistent with the designated response sequence of the first bus, the next request is not required to be sent after the response data of the previous request is returned, the request transmission is prevented from being blocked, and the request processing efficiency is improved. The system bandwidth utilization rate is improved.
It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.
Optionally, the embodiment of the invention further provides a bus bridge, which is respectively connected with the first device and the second device; the first device adopts a first bus, and the second device adopts a second bus; the bus bridge is used for executing the request processing method.
The number of the first devices may be plural, or may be one, which is not limited in the embodiment of the present invention. Specifically, a bus bridge refers to an architecture that enables communication between two different bus bridges.
Referring to fig. 2, a block diagram of a bus bridge of the present invention is shown, and as shown in fig. 2, fig. 2 uses a first bus as an AXI4 bus, a second bus as a TileLink bus, and a second device as an example of a processor:
The bus bridge can comprise a processing module (AXI 2 TLfragment) and a storage module (AXI 2 TL), and compared with the block pipeline bus bridge of AXI4 and TileLink widely used in the industry, the block pipeline bus bridge can be realized by using eight small modules, and the embodiment of the invention simplifies the design of the bus bridge and reduces the complexity. The AXI2TLFragment module is used to split the multi-bit transmission in AXI4 into single-bit transmissions and to convert the AXI4 single-bit response into the correct response in the multi-bit transmission. The AXI2TL module consists of a read reservation stack and a write reservation stack, each of which may contain a plurality of entries. The functions of the reservation stack include: storing user information of the AXI4 request, converting the AXI4 request into a tileLink request, temporarily storing a tileLink response, converting the tileLink response into an AXI response, and controlling the AXI response sequence to be consistent with the designated sequence of the AXI.
Specifically, after the processing module performs the first request (AXI request), the processing module may switch the multi-bit transmission of the AXI to single-bit transmission. A Multiplexer (MUX) may choose to enter either the first reservation stack (read reservation stack) or the second reservation stack (write reservation stack) depending on the request type of the first request. After the AXI request enters the reservation stack, an ID mapping can be performed and converted to a second request (TL request). The control TL requests are sent to the TL bus in a sending order (which may be FIFO) specified by AXI.
In particular, the read reservation stack may be coupled to an arbiter (Arb) for controlling the transmission of read requests in TL requests (TL Req) to the TL bus in a transmission order (which may be FIFO) specified by AXI. Specifically, the module a (sink a) is sent to the three-level cache of the processor and is used for receiving the a-channel request.
Further, the reservation stack may receive the response data of the TL bus and convert it into target response data (AXI response), which may include a target read response (RResp) and a target write response (wrest). The AXI response data may be filled into the corresponding entry according to sourceID addressing. Further, the read response arbiter (RRespArb) and the write response arbiter (WRespArb) may control the read reservation stack and the target response data in the write reservation stack to be returned to the AXI bus in the AXI specified response order, respectively.
Specifically, the read response data of the TL bus may be sent by a response channel module (SourceD) in the processor's three-level cache. Write response data for the TL bus may be sent by the B response channel module of the processor.
The bus bridge provided by the embodiment of the invention can break through the problem that the AXI requests with the same ID cannot be simultaneously sent to the TileLink bus based on the characteristics of the reserved stack. Although TileLink cannot guarantee that responses are returned in the order in which the requests were issued, the reservation stack can temporarily store AXI responses, and the state machine controls the AXI responses to be returned according to AXI order model rules. The transaction in flight of the entire system is now no longer limited to the AXI ID but depends on the depth of the reservation stack. In an extreme case, if the IDs of all AXI requests are the same, the bandwidth of the present invention is a multiple of the depth of the reservation stack of the bus bridge, and the requests with a multiple of the depth of the reservation stack can be processed at the same time.
Device embodiment
Referring to fig. 3, which shows a block diagram of an embodiment of a request processing apparatus according to the present invention, the apparatus 20 may specifically include:
a first storage module 201, configured to store a first request sent by a first bus in a preset reservation stack in response to receiving the first request;
a first conversion module 202, configured to convert a first request in the reservation stack into a second request conforming to a second bus, and send the second request in the reservation stack to the second bus;
a second conversion module 203, configured to convert response data sent by the second bus into response data conforming to the first bus as target response data in response to receiving the response data, and store the target response data in the reservation stack;
and the sending module 204 is configured to send the target response data in the reservation stack to the first bus according to the specified response sequence of the first bus.
Optionally, the reservation stack includes a first reservation stack and a second reservation stack; the first storage module 201 includes:
the first acquisition sub-module is used for acquiring the request type of the first request;
A first determination submodule, configured to determine a first target reservation stack from the first reservation stack and the second reservation stack based on the request type;
a second storage sub-module configured to store the first request in the first target reservation stack;
the second conversion module 203 includes:
the second acquisition sub-module is used for acquiring the response type of the target response data;
a second determination submodule, configured to determine a second target reservation stack from the first reservation stack and the second reservation stack based on the response type;
and the third storage sub-module is used for storing the target response data into the second target reservation stack.
Optionally, the apparatus further comprises:
the identifier generation module is used for generating a target identifier based on the request identifier of the first request, the request type of the first request and the storage index value of the first request in the reservation stack, and taking the target identifier as the request identifier of the second request;
the second conversion module 203 includes:
a third determining submodule, configured to determine a stored index value of a first request corresponding to the target response data in the reservation stack based on a response identifier of the target response data;
And the fourth storage sub-module is used for storing the target response data to the storage address indicated by the storage index value.
Optionally, the second storage sub-module is specifically configured to:
dividing the first request into a plurality of sub-requests;
and storing the plurality of sub-requests into the first target reservation stack in a single bit transmission mode.
The third storage sub-module is specifically configured to:
dividing the target response data into a plurality of sub-responses;
and storing the plurality of sub-responses into the second target reservation stack in a single bit transmission mode.
Optionally, the sending module includes:
a selecting sub-module, configured to select a plurality of sub-responses from the second target reservation stack according to the specified response sequence of the first bus, as sub-responses to be sent;
and the splicing sub-module is used for splicing the sub-responses to be sent to obtain responses to be sent, and sending the responses to be sent to the first bus.
Optionally, the first bus is an AXI bus, and the second bus is a TileLink bus.
In summary, the embodiment of the invention provides a request processing device, which responds to receiving a first request sent by a first bus and stores the first request into a preset reservation stack; converting the first request in the reservation stack into a second request conforming to a second bus, and sending the second request in the reservation stack to the second bus; in response to receiving response data sent by the second bus, converting the response data into response data conforming to the first bus as target response data, and storing the target response data in the reservation stack; and sending the target response data in the reservation stack to the first bus according to the designated response sequence of the first bus. Compared with the method that the next request is sent after the response sequence of the previous request is returned in the prior art, the request processing method provided by the embodiment of the invention can temporarily store the request and the response data by using the reservation stack through setting the reservation stack, and can realize rearrangement of the target response data in the reservation stack by sending the target response data in the reservation stack according to the appointed response sequence of the first bus, so that the return sequence of the response data is consistent with the appointed response sequence of the first bus, the next request is not required to be sent after the response data of the previous request is returned, the request transmission is prevented from being blocked, and the request processing efficiency is improved. The system bandwidth utilization rate is improved.
For system embodiments, the description is relatively simple as it is substantially similar to method embodiments, and reference is made to the description of method embodiments for relevant points.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
The specific manner in which the respective modules perform the operations in the request processing apparatus in the above-described embodiments has been described in detail in the embodiments concerning the method, and will not be described in detail here.
The embodiment of the invention also provides electronic equipment, which comprises: a processor, a memory for storing processor-executable instructions, wherein the processor is configured to perform the above-described request processing method.
Referring to fig. 4, a schematic structural diagram of an electronic device according to an embodiment of the present invention is shown. As shown in fig. 4, the electronic device includes: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus; the memory is configured to store at least one executable instruction, where the executable instruction causes the processor to perform the request processing method of the foregoing embodiment.
It should be noted that, the electronic device in the embodiment of the present application includes a mobile electronic device and a non-mobile electronic device.
The processor may be a CPU (Central Processing Unit ), general purpose processor, DSP (Digital Signal Processor ), ASIC (Application Specific Integrated Circuit, application specific integrated circuit), FPGA (Field-Programmable Gate Array, field programmable gate array) or other editable device, transistor logic, hardware components, or any combination thereof. The processor may also be a combination that performs the function of a computation, e.g., a combination comprising one or more microprocessors, a combination of a DSP and a microprocessor, etc.
The communication bus may include a path to transfer information between the memory and the communication interface. The communication bus may be a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus or an EISA (Extended Industry Standard Architecture ) bus, or the like. The communication bus may be classified into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one line is shown in fig. 4, but not only one bus or one type of bus.
The Memory may be a ROM (Read Only Memory) or other type of static storage device, a RAM (Random Access Memory) or other type of dynamic storage device, which may store static information and instructions, an EEPROM (Electrically Erasable Programmable Read Only, electrically erasable programmable Read Only Memory), a CD-ROM (Compact Disc Read-Only Memory), a magnetic tape, a floppy disk, an optical data storage device, etc.
Embodiments of the present invention also provide a non-transitory computer-readable storage medium, which when executed by a processor of an electronic device (server or terminal), enables the processor to perform the request processing method shown in fig. 1.
Embodiments of the present invention also provide a computer program product containing instructions that, when run on a computer, cause the computer to perform the request processing method shown in fig. 1.
The embodiment of the application also provides a chip, which comprises a processor and a communication interface, wherein the communication interface is coupled with the processor, and the processor is used for running programs or instructions to realize the processes of the embodiment of the request processing method, and can achieve the same technical effects, so that repetition is avoided, and the repeated description is omitted.
It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, chip systems, or system-on-chip chips, etc.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may be implemented, in whole or in part, in software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
It should be noted that, in the embodiment of the present application, the various data-related processes are all performed under the condition of conforming to the corresponding data protection rule policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The foregoing has described in detail the methods, apparatus, bus bridge, electronic device and readable storage medium for processing requests provided by the present invention, and specific examples have been applied to illustrate the principles and embodiments of the present invention, and the above examples are only used to help understand the methods and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. A method of request processing, the method comprising:
in response to receiving a first request sent by a first bus, storing the first request in a preset reservation stack;
converting the first request in the reservation stack into a second request conforming to a second bus, and sending the second request in the reservation stack to the second bus;
in response to receiving response data sent by the second bus, converting the response data into response data conforming to the first bus as target response data, and storing the target response data in the reservation stack;
And sending the target response data in the reservation stack to the first bus according to the designated response sequence of the first bus.
2. The method of claim 1, wherein the reservation stack comprises a first reservation stack and a second reservation stack; the storing the first request in a preset reservation stack includes:
acquiring a request type of the first request;
determining a first target reservation stack from the first reservation stack and the second reservation stack based on the request type;
storing the first request in the first target reservation stack;
the storing the target response data in the reservation stack includes:
acquiring a response type of the target response data;
determining a second target reservation stack from the first reservation stack and the second reservation stack based on the response type;
and storing the target response data into the second target reservation stack.
3. The method of claim 1, wherein after the converting the first request in the reservation stack to a second request conforming to a second bus, the method further comprises:
generating a target identifier based on the request identifier of the first request, the request type of the first request and the stored index value of the first request in the reservation stack, and taking the target identifier as the request identifier of the second request;
The storing the target response data in the reservation stack includes:
determining a storage index value of a first request corresponding to the target response data in the reservation stack based on the response identification of the target response data;
and storing the target response data to a storage address indicated by the storage index value.
4. The method of claim 2, wherein the storing the first request into the first target-reservation stack comprises:
dividing the first request into a plurality of sub-requests;
storing the plurality of sub-requests into the first target reservation stack in a single bit transmission manner;
the storing the target response data in the second target reservation stack includes:
dividing the target response data into a plurality of sub-responses;
and storing the plurality of sub-responses into the second target reservation stack in a single bit transmission mode.
5. The method of claim 4, wherein the sending the target response data in the reservation stack to the first bus in the specified response order of the first bus comprises:
selecting a plurality of sub-responses from the second target reservation stack according to the appointed response sequence of the first bus, and taking the sub-responses as sub-responses to be sent;
And splicing the sub-responses to be sent to obtain responses to be sent, and sending the responses to be sent to the first bus.
6. The method of any of claims 1-5, wherein the first bus is an AXI bus and the second bus is a TileLink bus.
7. A bus bridge, wherein the bus bridge is connected with a first device and a second device respectively; the first device adopts a first bus, and the second device adopts a second bus; the bus bridge is configured to perform the request processing method according to any one of claims 1 to 6.
8. A request processing apparatus, the apparatus comprising:
the first storage module is used for responding to the received first request sent by the first bus and storing the first request into a preset reservation stack;
the first conversion module is used for converting the first request in the reservation stack into a second request conforming to a second bus and sending the second request in the reservation stack to the second bus;
the second conversion module is used for responding to the received response data sent by the second bus, converting the response data into response data conforming to the first bus, taking the response data as target response data, and storing the target response data into the reservation stack;
And the sending module is used for sending the target response data in the reservation stack to the first bus according to the designated response sequence of the first bus.
9. An electronic device, comprising a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; the memory is configured to store executable instructions that cause the processor to perform the request processing method according to any one of claims 1 to 6.
10. A readable storage medium, characterized in that instructions in the readable storage medium, when executed by a processor of an electronic device, enable the processor to perform the request processing method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410090405.2A CN117632820B (en) | 2024-01-22 | 2024-01-22 | Request processing method, device, bus bridge, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410090405.2A CN117632820B (en) | 2024-01-22 | 2024-01-22 | Request processing method, device, bus bridge, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117632820A true CN117632820A (en) | 2024-03-01 |
| CN117632820B CN117632820B (en) | 2024-05-14 |
Family
ID=90016627
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410090405.2A Active CN117632820B (en) | 2024-01-22 | 2024-01-22 | Request processing method, device, bus bridge, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117632820B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102004709A (en) * | 2009-08-31 | 2011-04-06 | 国际商业机器公司 | Bus bridge between processor local bus (PLB) and advanced extensible interface (AXI) and mapping method |
| CN102609378A (en) * | 2012-01-18 | 2012-07-25 | 中国科学院计算技术研究所 | Message type internal memory accessing device and accessing method thereof |
| US20130042038A1 (en) * | 2011-08-08 | 2013-02-14 | Lsi Corporation | Non-blocking processor bus bridge for network processors or the like |
| CN105095104A (en) * | 2014-04-15 | 2015-11-25 | 华为技术有限公司 | Method and device for data caching processing |
| US10061540B1 (en) * | 2016-06-30 | 2018-08-28 | EMC IP Holding Company LLC | Pairing of data storage requests |
| CN110032335A (en) * | 2017-12-12 | 2019-07-19 | Arm有限公司 | The adjusting of atomic data access request |
| US20200401542A1 (en) * | 2018-05-31 | 2020-12-24 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for implementing data transmission, electronic device, and computer-readable storage medium |
| CN112637329A (en) * | 2020-12-21 | 2021-04-09 | 网络通信与安全紫金山实验室 | Identification method, device, equipment and storage medium of multiple application programs |
| CN113254368A (en) * | 2021-07-15 | 2021-08-13 | 苏州浪潮智能科技有限公司 | Data writing method and data reading method from AXI bus to OPB bus |
-
2024
- 2024-01-22 CN CN202410090405.2A patent/CN117632820B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102004709A (en) * | 2009-08-31 | 2011-04-06 | 国际商业机器公司 | Bus bridge between processor local bus (PLB) and advanced extensible interface (AXI) and mapping method |
| US20130042038A1 (en) * | 2011-08-08 | 2013-02-14 | Lsi Corporation | Non-blocking processor bus bridge for network processors or the like |
| CN102609378A (en) * | 2012-01-18 | 2012-07-25 | 中国科学院计算技术研究所 | Message type internal memory accessing device and accessing method thereof |
| CN105095104A (en) * | 2014-04-15 | 2015-11-25 | 华为技术有限公司 | Method and device for data caching processing |
| US10061540B1 (en) * | 2016-06-30 | 2018-08-28 | EMC IP Holding Company LLC | Pairing of data storage requests |
| CN110032335A (en) * | 2017-12-12 | 2019-07-19 | Arm有限公司 | The adjusting of atomic data access request |
| US20200401542A1 (en) * | 2018-05-31 | 2020-12-24 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for implementing data transmission, electronic device, and computer-readable storage medium |
| CN112637329A (en) * | 2020-12-21 | 2021-04-09 | 网络通信与安全紫金山实验室 | Identification method, device, equipment and storage medium of multiple application programs |
| CN113254368A (en) * | 2021-07-15 | 2021-08-13 | 苏州浪潮智能科技有限公司 | Data writing method and data reading method from AXI bus to OPB bus |
Non-Patent Citations (7)
| Title |
|---|
| HENRY COOK 等: "Diplomatic Design Patterns: A TileLink Case Study", 《CARRV’17》, 30 October 2017 (2017-10-30), pages 1 - 7, XP093036346 * |
| SIHAO LIU 等: "OverGen: Improving FPGA usability through domain-specific overlay generation", 《2022 55TH IEEE/ACM INTERNATIONAL SYMPOSIUM ON MICROARCHITECTURE》, 26 October 2022 (2022-10-26), pages 35 - 56, XP034214497, DOI: 10.1109/MICRO56248.2022.00018 * |
| 刘梦晓: "基三体系结构存储系统相关问题的研究", 《中国博士学位论文全文数据库 信息科技辑(月刊)》, no. 11, 15 November 2010 (2010-11-15), pages 137 - 2 * |
| 开芯小杨: "计算机体系结构——动态流水线&动态调度", pages 1 - 9, Retrieved from the Internet <URL:https://zhuanlan.zhihu.com/p/673823823> * |
| 张媛媛 等: "多路高速数据缓存器应用分析", 《空间电子技术》, no. 4, 25 December 2008 (2008-12-25), pages 22 - 25 * |
| 江文 等: "通过缓存压缩提高磁盘性能", 《小型微型计算机系统》, no. 5, 15 May 2016 (2016-05-15), pages 224 - 228 * |
| 汪安东: "基于CPLD的通用PCI扩展总线桥设计", 《世界电子元器件》, 1 May 2004 (2004-05-01), pages 71 - 73 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117632820B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647480B (en) | Data processing method, remote direct access network card and equipment | |
| US9940020B2 (en) | Memory management method, apparatus, and system | |
| CN114556881B (en) | Address translation method and device | |
| CN112631742B (en) | Resource access authority management device, method and system | |
| CN111984204B (en) | Data reading and writing method and device, electronic equipment and storage medium | |
| US10613783B2 (en) | Techniques for managing data which is accessible by multiple storage processors | |
| CA3139693A1 (en) | Dynamic allocation of computing resources | |
| CN109388651B (en) | Data processing method and device | |
| CN115114042A (en) | Storage data access method and device, electronic equipment and storage medium | |
| CN117632820B (en) | Request processing method, device, bus bridge, electronic equipment and readable storage medium | |
| US7657682B2 (en) | Bus interconnect with flow control | |
| CN111209263A (en) | Data storage method, device, equipment and storage medium | |
| CN116467081A (en) | Data processing method, device, equipment and computer readable storage medium | |
| CN115878333A (en) | Method, device and equipment for judging consistency between process groups | |
| CN116775510B (en) | Data access method, device, server and computer readable storage medium | |
| KR102349245B1 (en) | Data accessing method and apparatus, electronic device and computer storage medium | |
| CN115297169B (en) | Data processing method, device, electronic equipment and medium | |
| CN118012517B (en) | Network card interrupt configuration method, device and storage medium based on Feiteng platform multipath server | |
| CN112711545B (en) | Data access method based on array linked list type queue structure | |
| CN111163088B (en) | Message processing method, system and device and electronic equipment | |
| CN118277126A (en) | Read request processing method, broadcast unit and processor system | |
| CN117891506A (en) | Communication method, device and system | |
| CN114764489A (en) | Tensor processing method, device, equipment and computer readable storage medium | |
| CN117724654A (en) | Data storage method, data reading method, device and system and electronic equipment | |
| CN111030856A (en) | Cloud-based data access method, electronic device and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |