Software program refreshing and order-preserving method based on lookup table, electronic equipment and medium

Abstract

The invention relates to the technical field of chips, in particular to a software program refreshing and order-preserving method based on a lookup table, electronic equipment and a medium, and the method comprises the following steps: S1, obtaining a to-be-processed software program group {A1, A2,..., An,..., AN}; s2, setting a corresponding lookup table Bn for each An in downstream equipment; s3, the upstream device sends the instruction in each Ain to the downstream device according to the sequence of A1n, A2n,..., Ain,..., Af (n) n, when the instruction in one Ain is sent, an event Ei corresponding to the Ain is sent, and then the instruction in the next Ain continues to be sent; and S4, in the current clock period, updating the lookup table, and executing corresponding software program refreshing according to event information output by the lookup table. According to the method, the hardware resource consumption in the software program refreshing and order-preserving process is reduced, and the execution efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of chip technology, and in particular to a software program refresh and order preservation method based on lookup tables, an electronic device, and a medium. Background Technology

[0002] During software program execution, software program refreshes must be performed in the correct order; otherwise, errors may occur. However, multiple processes may occur simultaneously on upstream devices, and each process may execute a different number of instructions (waves). The execution units (APs) on downstream devices may return instructions out of order, further disrupting the order of processes and making it impossible to maintain the correct order during software program refresh. Current technologies require recording tag information for each instruction and monitoring its execution status based on that tag information. This necessitates multiple interactions between upstream and downstream devices to maintain the correct order, consuming significant hardware resources and exhibiting low efficiency. Therefore, reducing hardware resource consumption and improving execution efficiency during software program refresh and maintaining order is a pressing technical problem that needs to be addressed. Summary of the Invention

[0003] The purpose of this invention is to provide a software program refresh and order preservation method, electronic device, and medium based on a lookup table, which reduces the hardware resource consumption during the software program refresh and order preservation process and improves execution efficiency.

[0004] According to a first aspect of the present invention, a software program refresh and order preservation method based on a lookup table is provided, comprising: Step S1: Obtain the software program group to be processed {A1, A2, ..., A...} n ,...,A N}, A n Let A be the nth software program group to be processed, where n ranges from 1 to N, and N is the total number of software program groups to be processed. n ={A1 n A2 n ,...,A i n ,...,A f(n) n}, A i n For A n The corresponding i-th software program to be processed, where i ranges from 1 to f(n), and f(n) is A n The corresponding number of software programs to be processed, for each A i n It includes multiple instructions, different A n They are independent of each other, and the same A n A1 inn A2 n ,...,A i n ,...,A f(n) n The software program needs to be refreshed while maintaining its original order. Step S2, in the downstream equipment for each A n Set up a corresponding lookup table B. n B n Includes r(n) storage units {D1 n D2 n ,...,D j n ,...,D r(n) n}, D j n For B n The j-th storage unit, D j n Located in B n The j-th row, where the value of j ranges from 1 to r(n); Step S3, upstream equipment according to A1 n A2 n ,...,A i n ,...,A f(n) n The order will be each A i n The instructions in the middle are sent to the downstream device, and when an A i n When the instructions in the middle are finished being sent, send A. i n Corresponding event E i Then continue sending the next A i n Instructions in the text; Step S4, in the current clock cycle: If A is received n If a command or event is received, the downstream device will store the corresponding command or event information in the corresponding D according to the order of receiving the command and event. j n middle; If there is an instruction that has been executed, then from the corresponding D... j n The corresponding instruction information is read from the middle; If D1 n If it is event information, then D1 nThe corresponding event information is actively output and fed back to the upstream device. The upstream device executes the corresponding software program to refresh based on the received event information. If the read is followed by the write of B n If the stored content in B is not contiguous, then... n The stored content is adjusted to a continuous state while maintaining the original order of the stored content.

[0005] According to a second aspect of the present invention, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being configured to perform the method described in the first aspect of the present invention.

[0006] According to a third aspect of the present invention, a computer-readable storage medium is provided, storing computer-executable instructions for performing the method described in the first aspect of the present invention.

[0007] Compared with existing technologies, this invention has significant advantages and beneficial effects. Through the above technical solution, the software program refresh and order preservation method, electronic device, and medium provided by this invention based on a lookup table achieve considerable technological advancement and practicality, and have broad industrial application value. It has at least the following beneficial effects: This invention maintains a corresponding lookup table for each group of software programs to be processed. The lookup table records the sending order of instructions and events in the software programs to be processed within the group. Event information is actively output and fed back to the upstream device. The upstream device executes the corresponding software program refresh based on the received event information, thereby achieving software program refresh and order preservation. This reduces the number of interactions between upstream and downstream devices, lowers the hardware resource consumption during the software program refresh and order preservation process, and improves execution efficiency. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 The flowchart illustrates the software program refresh and order preservation method based on a lookup table provided in this embodiment of the invention. Detailed Implementation

[0010] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0011] This invention provides a software program refresh and order preservation method based on a lookup table, such as... Figure 1 As shown, it includes: Step S1: Obtain the software program group to be processed {A1, A2, ..., A...} n ,...,A N}, A n Let A be the nth software program group to be processed, where n ranges from 1 to N, and N is the total number of software program groups to be processed. n ={A1 n A2 n ,...,A i n ,...,A f(n) n}, A i n For A n The corresponding i-th software program to be processed, where i ranges from 1 to f(n), and f(n) is A n The corresponding number of software programs to be processed, for each A i n It includes multiple instructions, different A n They are independent of each other, and the same A n A1 in n A2 n ,...,A i n ,...,A f(n) n The software program needs to be refreshed while maintaining its original order.

[0012] Among them, A1 n A2 n ,...,A i n ,...,A f(n) n The requirement to maintain the order of the software program refresh refers to A1. n We need to wait for A1 n A1 can only be executed after all other instructions in the code have been completed. n The corresponding execution software program is refreshed. A2 n We need to wait for A2 n and A1 nA2 can only be executed after all other instructions in the code have been completed. n The corresponding execution software program is refreshed. ...A i n Need to wait for A i n and A1 n To A i-1 n A can only be executed after all other instructions in the process have been completed. i n The corresponding execution software program is refreshed.

[0013] Step S2, in the downstream equipment for each A n Set up a corresponding lookup table B. n B n Includes r(n) storage units {D1 n D2 n ,...,D j n ,...,D r(n) n}, D j n For B n The j-th storage unit, D j n Located in B n The j-th row, where the value of j ranges from 1 to r(n).

[0014] In one preferred embodiment, all values ​​of r(n) are equal, r(n)≤Q, where Q is the total number of computing units. The hardware resources of the downstream device include X execution units (Accelerated Processors, abbreviated as AP), each execution unit includes Y processing units (Procesor Element Units, abbreviated as PEU), each computing unit includes Z computing units, and each computing unit can run one instruction, Q=X×Y×Z.

[0015] Step S3, upstream equipment according to A1 n A2 n ,...,A i n ,...,A f(n) n The order will be each A i n The instructions in the middle are sent to the downstream device, and when an A i n When the instructions in the middle are finished being sent, send A. i n Corresponding event E i Then continue sending the next Ai n The instructions in the text.

[0016] It should be noted that corresponding events were inserted between two adjacent software programs to be processed.

[0017] Step S4, in the current clock cycle: If A is received n If a command or event is received, the downstream device will store the corresponding command or event information in the corresponding D according to the order of receiving the command and event. j n middle.

[0018] If there is an instruction that has been executed, then from the corresponding D... j n The corresponding instruction information is read from it.

[0019] If D1 n If it is event information, then D1 n The corresponding event information is actively output and fed back to the upstream device. The upstream device executes the corresponding software program to refresh based on the received event information.

[0020] If the read is followed by the write of B n If the stored content in B is not contiguous, then... n The stored content is adjusted to a continuous state while maintaining the original order of the stored content.

[0021] As one example, B n Including pointer C n C n The initial value is set to 1, indicating that the pointer points to D1. n B n Each storage unit includes status information, and the initial status information of each storage unit is invalid, D1 n D2 n ,...,D j n ,...,D r(n) n Arranged from bottom to top.

[0022] It should be noted that when for each A n Set the corresponding B n Then, within each clock cycle, B is updated according to different situations. n The following describes each case in detail through different embodiments.

[0023] Example 1 In step S4, if only A is received in the current clock cycle... nIf the command or event information in the code is correct, then execute: Step S41, downstream device is A n The instructions or events in the process allocate computing resources and generate A n The instruction or event information in the instruction or event is the instruction information or event information corresponding to the instruction or event. The instruction information includes the instruction identifier and the corresponding hardware resource information. The event information includes the event identifier and the corresponding hardware resource information. The hardware resource information includes the execution unit identifier, the arithmetic unit identifier and the computing unit identifier. The execution unit includes multiple arithmetic units, and the arithmetic unit includes multiple computing units. Each computing unit is used to execute one instruction.

[0024] It should be noted that one clock cycle A n Only one instruction or one event can be issued; therefore, only one A can be received in one clock cycle. n A single instruction or event will not be received simultaneously. Furthermore, the instruction information establishes a mapping between instructions and their corresponding hardware resource information, while the event information establishes a mapping between events and their corresponding hardware resource information. This allows for accurate identification of which instruction has completed execution when a hardware resource finishes executing its corresponding instruction, and for accurate identification of which hardware resource has been released when event information is output from the lookup table or instruction information is read from the lookup table.

[0025] Step S42: The downstream device will generate A n Write instruction or event information to C n In the currently pointed-to memory unit, set the corresponding memory unit status information to valid, and update C. n =C n +1.

[0026] Example 2 In step S4, if there is only one instruction that has been completed in the current clock cycle, then the following is executed: Step C41: From the D corresponding to the executed instruction j n The corresponding instruction information is read from the middle, and the D corresponding to the executed instruction is released. j n .

[0027] Step C42: The D corresponding to the executed instruction. j n The contents of the storage units with valid status information are shifted down one storage unit in sequence.

[0028] It should be noted that the D corresponding to the executed instruction... j nThe above status information indicates that the contents of the memory cells in the valid state are shifted down one memory cell at a time. This means that the contents of the memory cells corresponding to the completed instructions will be shifted down one memory cell at a time. j n The above state information is the valid state D. j+1 n The data content in D covers j n The data content is processed in ascending order of the j value.

[0029] Step C43, Update C n =C n -1 will update C n The status information of the memory cell being pointed to is set to invalid.

[0030] Example 3 In step S4, if only D1 exists in the current clock cycle... n If the information is an event message, then execute: Step D41, D1 n The corresponding event information is actively output and fed back to the upstream device. The upstream device executes the corresponding software program to refresh based on the received event information.

[0031] It should be noted that when a device receives an event message, it means that all previous instructions corresponding to the event message have been executed. At this time, the corresponding software program can be refreshed based on the received event message, ensuring the ordered execution of the software program refresh.

[0032] Step D42, D1 n The contents of the storage units with valid status information are shifted down one storage unit in sequence.

[0033] It should be noted that D1 n The above status information indicates that the contents of the storage unit in the valid state are shifted down one storage unit. This means that D1 is... n The above state information is the valid state D. j+1 n The data content in D covers j n The data content is processed in ascending order of the j value.

[0034] Step D43, Update C n =C n -1 will update C n The status information of the memory cell being pointed to is set to invalid.

[0035] Example 4 In step S4, if, during the current clock cycle, both of the following conditions are met: A is received... n If the instruction or event information in the data contains a completed instruction, then execute: Step E41, downstream device is A n The instructions or events in the process allocate computing resources and generate A n The instruction or event information in the instruction or event is the instruction information or event information corresponding to the instruction or event. The instruction information includes the instruction identifier and the corresponding hardware resource information. The event information includes the event identifier and the corresponding hardware resource information. The hardware resource information includes the execution unit identifier, the arithmetic unit identifier and the computing unit identifier. The execution unit includes multiple arithmetic units, and the arithmetic unit includes multiple computing units. Each computing unit is used to execute one instruction.

[0036] Step E42: The downstream device will generate A n Write instruction or event information to C n In the currently pointed-to memory location, C n Keep it unchanged, and put C n The status information of the memory cell being pointed to is set to a valid state.

[0037] Step E43: From the D corresponding to the executed instruction j n The corresponding instruction information is read from the middle, and the D corresponding to the executed instruction is released. j n .

[0038] Step E44: Transfer the D corresponding to the executed instruction. j n The contents of the storage units with valid status information are shifted down one storage unit in sequence.

[0039] It should be noted that the D corresponding to the executed instruction... j n The above status information indicates that the contents of the memory cells in the valid state are shifted down one memory cell at a time. This means that the contents of the memory cells corresponding to the completed instructions will be shifted down one memory cell at a time. j n The above state information is the valid state D. j+1 n The data content in D covers j n The data content is processed in ascending order of the j value.

[0040] Step E45, place C n The status information of the memory cell being pointed to is set to invalid.

[0041] Example 5 In step S4, if, during the current clock cycle, both of the following conditions are met: A is received... n Instruction or event information in D1 n If it is event information, then execute: Step F41, downstream device is A n The instructions or events in the process allocate computing resources and generate A n The instruction or event information in the instruction or event is the instruction information or event information corresponding to the instruction or event. The instruction information includes the instruction identifier and the corresponding hardware resource information. The event information includes the event identifier and the corresponding hardware resource information. The hardware resource information includes the execution unit identifier, the arithmetic unit identifier and the computing unit identifier. The execution unit includes multiple arithmetic units, and the arithmetic unit includes multiple computing units. Each computing unit is used to execute one instruction.

[0042] Step F42, the downstream device will generate A n Write instruction or event information to C n In the currently pointed-to memory location, C n Keep it unchanged, and put C n The status information of the memory cell being pointed to is set to a valid state.

[0043] Step F43, D1 n The corresponding event information is actively output and fed back to the upstream device. The upstream device executes the corresponding software program to refresh based on the received event information.

[0044] It should be noted that when a device receives an event message, it means that all previous instructions corresponding to the event message have been executed. At this time, the corresponding software program can be refreshed based on the received event message, ensuring the ordered execution of the software program refresh.

[0045] Step F44, D1 n The contents of the storage units with valid status information are shifted down one storage unit in sequence.

[0046] It should be noted that D1 n The above status information indicates that the contents of the storage unit in the valid state are shifted down one storage unit. This means that D1 is... n The above state information is the valid state D. j+1 n The data content in D covers j n The data content is processed in ascending order of the j value.

[0047] Step F45, place C n The status information of the memory cell being pointed to is set to invalid.

[0048] Example 6 In step S4, if, during the current clock cycle, both of the following conditions are met: A is received... n The instruction or event information in the D1, the existence of an instruction that has completed execution, D1 n If it is event information, then execute: Step G41, D1 n The corresponding event information is actively output and fed back to the upstream device. The upstream device executes the corresponding software program to refresh based on the received event information.

[0049] It should be noted that when a device receives an event message, it means that all previous instructions corresponding to the event message have been executed. At this time, the corresponding software program can be refreshed based on the received event message, ensuring the ordered execution of the software program refresh.

[0050] Step G42, from the D corresponding to the executed instruction j n The corresponding instruction information is read from the middle, and the D corresponding to the executed instruction is released. j n .

[0051] Step G43, downstream device is A n The instructions or events in the process allocate computing resources and generate A n The instruction or event information in the instruction or event is the instruction information or event information corresponding to the instruction or event. The instruction information includes the instruction identifier and the corresponding hardware resource information. The event information includes the event identifier and the corresponding hardware resource information. The hardware resource information includes the execution unit identifier, the arithmetic unit identifier and the computing unit identifier. The execution unit includes multiple arithmetic units, and the arithmetic unit includes multiple computing units. Each computing unit is used to execute one instruction.

[0052] Step G44: The downstream device will generate A n Write instruction or event information to C n In the currently pointed-to memory location, C will be... n The status information of the memory cell being pointed to is set to a valid state.

[0053] Step G45: Transfer the D corresponding to the executed instruction. j n The contents of the following storage units are shifted down one storage unit at a time.

[0054] It should be noted that D1 n The above status information indicates that the contents of the storage unit in the valid state are shifted down one storage unit. This means that D1 is... n The above state information is the valid state D. j+1 n The data content in D coversj n The data content is processed in ascending order of the j value.

[0055] Step G46: Transfer the D corresponding to the executed instruction. j n The contents of the storage units with valid status information are shifted down two storage units in sequence.

[0056] It should be noted that the D corresponding to the executed instruction... j n The contents of the memory cells with valid status information are shifted down two memory cells sequentially, and the D corresponding to the executed instruction is moved down. j n The above state information is the valid state D. j+2 n The data content in D covers j n The data content is processed in ascending order of the j value.

[0057] Step G47, Update C n =C n -1 will update C n The memory unit pointed to and C n The status information of the storage cell corresponding to +1 is set to invalid.

[0058] Example 7 In step S4, during the current clock cycle, if simultaneously: there exists a completed instruction, D1... n If the information is an event message, then execute: Step H41, D1 n The corresponding event information is actively output and fed back to the upstream device. The upstream device executes the corresponding software program to refresh based on the received event information.

[0059] It should be noted that when a device receives an event message, it means that all previous instructions corresponding to the event message have been executed. At this time, the corresponding software program can be refreshed based on the received event message, ensuring the ordered execution of the software program refresh.

[0060] Step H42, from the D corresponding to the executed instruction j n The corresponding instruction information is read from the middle, and the D corresponding to the executed instruction is released. j n .

[0061] Step H43: Transfer the D corresponding to the executed instruction. j nThe contents of the following storage units are shifted down one storage unit at a time.

[0062] It should be noted that the D corresponding to the executed instruction... j n The above status information indicates that the contents of the memory cells in the valid state are shifted down one memory cell at a time. This means that the contents of the memory cells corresponding to the completed instructions will be shifted down one memory cell at a time. j n The above state information is the valid state D. j+1 n The data content in D covers j n The data content is processed in ascending order of the j value.

[0063] Step H44: D corresponding to the executed instruction j n The contents of the storage units with valid status information are shifted down two storage units in sequence.

[0064] It should be noted that the D corresponding to the executed instruction... j n The contents of the memory cells with valid status information are shifted down two memory cells sequentially, and the D corresponding to the executed instruction is moved down. j n The above state information is the valid state D. j+2 n The data content in D covers j n The data content is processed in ascending order of the j value.

[0065] Step H45, Update C n =C n -2, will update C n The memory unit pointed to and C n The status information of the storage cell corresponding to +1 is set to invalid.

[0066] It should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the steps as sequential processes, many of these steps can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the steps can be rearranged. A process can be terminated when its operation is complete, but it may also have additional steps not included in the figures. A process can correspond to a method, function, procedure, subroutine, subroutine, etc.

[0067] This invention also provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being configured to perform the method described in this invention.

[0068] This invention also provides a computer-readable storage medium storing computer-executable instructions for performing the methods described in this invention.

[0069] In this embodiment of the invention, a corresponding lookup table is maintained for each group of software programs to be processed. The lookup table records the sending order of instructions and events in the software programs to be processed within the group. Event information is actively output and fed back to the upstream device. The upstream device executes the corresponding software program refresh based on the received event information, thereby achieving software program refresh and order preservation. This reduces the number of interactions between the upstream and downstream devices, reduces the hardware resource consumption during the software program refresh and order preservation process, and improves execution efficiency.

[0070] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for software program refresh preserving order based on lookup table, characterized in that, Comprising: Step S1, obtaining a set of software programs to be processed {A1, A2,..., An}, An is the nth software program to be processed, n is in the range of 1 to N, N is the total number of software programs to be processed, An={A1, A2,..., Af(n)}, Af(n) is the ith software program to be processed corresponding to An, i is in the range of 1 to f(n), f(n) is the number of software programs to be processed corresponding to An, each An includes a plurality of instructions, different An are independent of each other, A1, A2,..., Af(n) in the same An are independent of each other, and the software program needs to be refreshed in order. n N n n n n i n f(n) n i n n n i n n n n n i n f(n) n The software program needs to be refreshed in order.​​​​​​​​​​​​​​​​​ Step S2, the downstream device sets up a corresponding look-up table B n for each A n n including r(n) storage units {D1 n ,D2 n ,...,D j n ,...,D r(n) n}, D j n is the jth storage unit of B n , D j n is located in the jth row of B n , j ranges from 1 to r(n);​ Step S3, upstream equipment according to A1 n A2 n ,...,A i n ,...,A f(n) n The order will be each A i n The instructions in the middle are sent to the downstream device, and when an A i n When the instructions in the middle are finished being sent, send A. i n Corresponding event E i Then continue sending the next A i n Instructions in the text; Step S4, in the current clock cycle: If there is an instruction or event received in A n , the downstream device stores the corresponding instruction information or event information in the corresponding D j in order according to the order of the received instructions and events. n If there is an executed instruction, the corresponding instruction information is read out from the D j n memory 1000. If D1 n is event information, the corresponding event information in D1 n is actively outputted, and feedback is given to the upstream device, and the upstream device executes corresponding software program refreshing based on the received event information; If the contents stored in B n after the read are not continuous, the contents stored in B n are adjusted to be continuous and the order of the stored contents is maintained.

2. The method of claim 1, wherein, B n includes a pointer C n , C n is initially set to 1, indicating that the pointer points to D1 n , B n Each storage unit includes state information, and the state information of each storage unit is initially invalid, D1 n , D2 n ,..., D j n ,..., D r(n) n is arranged in turn from bottom to top.

3. The method of claim 2, wherein, In the step S4, in the current clock cycle, if only the instruction or event information received in the A n is executed. Step S41, the downstream device is A n assigning computing resources to instructions or events in the A n corresponding instruction information or event information of the instructions or events, the instruction information including instruction identifiers and corresponding hardware resource information, the event information including event identifiers and corresponding hardware resource information, the hardware resource information including execution unit identifiers, operation unit identifiers and computing unit identifiers, the execution unit including multiple operation units, the operation unit including multiple computing units, and each computing unit being configured to execute one instruction; Step S42, the downstream device writes the generated A n instruction information or event information into the C n current pointing storage unit, and sets the corresponding storage unit state information to the valid state, updates the C n =C n +1.

4. The method of claim 2, wherein, In the step S4, in the current clock cycle, if there is only one executed instruction, then execute: Step C41, read out the corresponding instruction information from the D j n j n ;​ Step C42, the D j n The contents of the storage units in the valid state are moved down one storage unit at a time. Step C43, update C n = C n -1, the state information of the storage unit pointed to by the updated C n is set to an invalid state; Alternatively, in the step S4, at the current clock cycle, if only D1 n For event information, then execute: Step D41, D1 n corresponding event information is actively outputted and fed back to the upstream device, and the upstream device executes corresponding software program refreshing based on the received event information; Step D42, D1 n The contents of the storage units in the valid state are moved down one storage unit at a time. Step D43, update C n = C n -1, the state information of the storage unit pointed to by the updated C n is set to the invalid state.

5. The method of claim 2, wherein, In the step S4, in the current clock cycle, if the following two conditions exist simultaneously: the instruction or event information in the A n is received, and there is an executed instruction, then the following is executed: Step E41, the downstream device is A n the instructions or events in the computing resource allocation, generating A n the instructions or events in the instruction information or event information corresponding to the instruction, the instruction information includes instruction identification and corresponding hardware resource information, the event information includes event identification and corresponding hardware resource information, the hardware resource information includes execution unit identification, operation unit identification and computing unit identification, the execution unit includes a plurality of operation units, the operation unit includes a plurality of computing units, and each computing unit is used to execute an instruction; Step E42, the downstream device writes the generated A n instruction information or event information to the C n current storage unit, the C n remains unchanged, the C n state information of the storage unit pointed to is set to the valid state; Step E43, the corresponding instruction information is read out from the D j n corresponding to the executed instruction, and the D j n ; Step E44, the D j n The contents of the storage units in the valid state are moved down one storage unit at a time. Step E45, place C n The status information of the memory cell being pointed to is set to invalid.

6. The method of claim 2, wherein, In the step S4, in the current clock cycle, if both of the following conditions exist simultaneously: the instruction or event information in the D1 n buffer is received, and the D1 n buffer contains event information, then the following is executed: Step F41, the downstream device is A n the instructions or events in the computing resource allocation, generating A n the instructions or events in the instruction information or event information corresponding to the instructions or events, the instruction information includes instruction identifier and corresponding hardware resource information, the event information includes event identifier and corresponding hardware resource information, the hardware resource information includes execution unit identifier, operation unit identifier and computing unit identifier, the execution unit includes a plurality of operation units, the operation unit includes a plurality of computing units, and each computing unit is used for executing an instruction; Step F42, the downstream device writes the generated A n instruction information or event information into C n the currently pointed storage unit, C n remains unchanged, C n the state information of the pointed storage unit is set to the valid state; Step F43, D1 n corresponding event information is actively outputted and fed back to the upstream device, and the upstream device executes corresponding software program refreshing based on the received event information; Step F44, D1 n The contents of the storage units in the valid state are moved down one storage unit at a time. Step F45, place C n The status information of the memory cell being pointed to is set to invalid.

7. The method of claim 2, wherein, In the step S4, in the current clock cycle, if there exist simultaneously: the instruction or event information received in the A n buffer, one executed instruction, and the D1 n event information, then the following is executed: Step G41, D1 n corresponding event information is actively outputted and fed back to the upstream device, and the upstream device executes corresponding software program refreshing based on the received event information; Step G42, read out the corresponding instruction information from the D j n j n ;​ Step G43, the downstream device is A n the instructions or events in the computing resource allocation, generating A n the instructions or events in the instruction information or event information corresponding to the instructions or events, instruction information includes instruction identifier and corresponding hardware resource information, event information includes event identifier and corresponding hardware resource information, hardware resource information includes execution unit identifier, operation unit identifier and computing unit identifier, execution unit includes multiple operation units, operation unit includes multiple computing units, each computing unit is used to execute an instruction; Step G44: The downstream device will generate A n Write instruction or event information to C n In the currently pointed-to memory location, C will be... n Set the status information of the pointed-to memory cell to a valid state; Step G45, the D j n The contents of the following storage units are successively moved down by one storage unit. Step G46, the D j n The contents of the storage units in the above state information for valid state are sequentially moved down two storage units; Step G47, update C n = C n -1, the updated C n points to, and the state information of the storage unit corresponding to C n +1 is set to the invalid state.

8. The method of claim 2, wherein, In the step S4, in the current clock cycle, if there exist simultaneously: an executed instruction, D1 n For event information, then execute: Step H41, D1 n corresponding event information is actively outputted and fed back to the upstream device, and the upstream device executes corresponding software program refreshing based on the received event information; Step H42, read out the corresponding instruction information from the D j n j n ;​ Step H43, the D j n The contents of the following storage units are successively moved down by one storage unit. Step H44, the D j n The contents of the storage units in the valid state are moved down two storage units in turn. Step H45, update C n = C n -2, the updated C n pointed to by the storage unit and C n +1, the state information of the storage unit corresponding thereto is set to the invalid state.

9. An electronic device, comprising: Comprising: At least one processor; And a memory connected in communication with the at least one processor; Wherein the memory stores instructions executed by the at least one processor, the instructions are set to execute the method of any one of the preceding claims 1-8.

10. A computer-readable storage medium, characterized in that, Computer executable instructions are stored, the computer executable instructions are used to execute the method of any one of the preceding claims 1-8.

Images