Automatic parallel simulation method and device for integrated circuits

The automatic parallel simulation method optimizes integrated circuit simulations by using a control server for intelligent queuing and resource allocation, addressing inefficiencies in computing power and data transfer to enhance simulation efficiency and speed.

JP2024543115AActive Publication Date: 2024-11-19BATELAB CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
JP2024530014
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2022-01-06
Filing Date
2023-01-03
Publication Date
2024-11-19
Estimated Expiration
2043-01-03

AI Technical Summary

Technical Problem

Existing integrated circuit simulation methods face inefficiencies due to limited computing power of local computers, manual intervention in simulation order prioritization, and large data file transfers that consume network bandwidth, reducing the overall efficiency of the simulation process.

Method used

An automatic parallel simulation method and device that utilizes a control server to manage simulation requests through intelligent queuing, sorting based on remaining simulation time and acceleration parameters, and distributing tasks to simulation servers to optimize resource allocation and minimize data transfer.

Benefits of technology

The method enhances simulation efficiency by ensuring timely and optimal utilization of simulation resources, reducing manual intervention, and minimizing data transfer, thereby improving the speed and completeness of integrated circuit simulations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024543115000001_ABST
    Figure 2024543115000001_ABST
Patent Text Reader

Abstract

The present application relates to an automatic parallel simulation method and a simulation device for integrated circuits, particularly to the field of electrical digital data processing. The method includes the steps of obtaining a circuit simulation request, adding the circuit simulation request to a first queuing queue as a simulation request candidate, performing a first sorting process on each simulation request candidate based on the remaining simulation time of each simulation request candidate to obtain a second queuing queue, performing a second sorting process on the second queuing queue according to the magnitude of the acceleration parameter of the simulation request candidate to obtain a target queuing queue, and performing simulation processing on each simulation request candidate by each simulation server within a target processing period according to the priority indicated by the target queuing queue. In the above embodiment, an intelligent queuing simulation is performed on each simulation request based on the performance of the simulation server, the demand of the target user, the simulation execution time, etc., and the efficiency of integrated circuit simulation is improved by appropriately allocating and utilizing the resources of the simulation server.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] This application claims priority to a Chinese patent application filed with the China Patent Office on January 6, 2022, bearing application number 202210007453.1 and entitled "Automated Integrated Circuit Parallel Simulation Method," the entire contents of which are incorporated herein by reference.

[0002] The present application relates to the field of electrical digital data processing, and in particular to a method and apparatus for automatic parallel simulation of integrated circuits. [Background technology]

[0003] In the prior art, after an engineer completes the design of a circuit structure of an integrated circuit using EDA software, the engineer usually needs to simulate the circuit using the EDA software to verify the accuracy of the circuit.

[0004] In order to solve the problem of limited computing power of the local computer, multiple simulation servers can be set up, and after an engineer completes the design of a circuit structure with EDA software, he submits a simulation request to the simulation server and uses the simulation server to simulate the circuit. This method solves the problem of low computing power of the local computer, and the multiple simulation servers can sort the simulation according to the order in which engineers submit the circuit simulation requests, and can provisionally adjust the simulation order with the assistance of manual intervention.

[0005] In the above embodiment, manual intervention has a certain subjectivity and makes it difficult to timely determine the priority order that needs to be adjusted, so that an excellent circuit design obtained through long-term consideration cannot obtain simulation resources in a timely manner, resulting in low efficiency of integrated circuit simulation.

[0006] In addition, the data files obtained by the simulation calculation are generally very large files, often occupying hundreds of gigabytes of storage space. Therefore, directly transferring the data files obtained by the simulation calculation between simulation servers requires occupying a large network bandwidth, which further affects the efficiency of integrated circuit simulation. Summary of the Invention [Problem to be solved by the invention]

[0007] The present application provides an automatic parallel simulation method and simulation device for an integrated circuit that improves the efficiency of integrated circuit simulation, and its technical solutions are as follows: [Means for solving the problem]

[0008] In one embodiment, the present invention is used in a control server in a simulation system further including each simulation server, obtaining a circuit simulation request for requesting a simulation resource to simulate an integrated circuit structure; adding the circuit simulation request to a first queuing queue as a simulation request candidate; performing a first sorting process on each simulation request candidate in the first queuing queue based on a remaining simulation time of each simulation request candidate in the first queuing queue to obtain a second queuing queue; performing a second sorting process on the second queuing queue according to the magnitude of an acceleration parameter of each simulation request candidate in the second queuing queue to obtain a target queuing queue; performing simulation processing for each of the simulation request candidates by each of the simulation servers within a target processing period according to the priority indicated by the target queuing queue.

[0009] In another aspect, a simulation request acquisition module for acquiring a circuit simulation request for requesting a simulation resource to simulate an integrated circuit structure; a first queue acquisition module for adding the circuit simulation request as a simulation request candidate to a first queuing queue; a second queue acquisition module for performing a first sorting process on each simulation request candidate in the first queuing queue based on a remaining simulation time of each simulation request candidate in the first queuing queue to obtain a second queuing queue; a target queue acquisition module that performs a second sorting process on the second queuing queue according to the magnitude of an acceleration parameter of each simulation request candidate in the second queuing queue to obtain a target queuing queue; a simulation processing module for performing simulation processing for each of the simulation request candidates by each of the simulation servers within a target processing period in accordance with the priority indicated by the target queuing queue.

[0010] In one possible embodiment, the remaining simulation time is used to indicate remaining processing progress of candidate simulation requests whose simulation has started before the target processing period; The apparatus further includes a remaining time determining module that determines a remaining simulation time of a newly started candidate simulation request obtained within a target processing period to be zero.

[0011] In one possible embodiment, the simulation processing module further comprises: A step of extracting a designated number of simulation request candidates according to the priority indicated by the target queuing queue, and performing acceleration point detection for the designated number of simulation request candidates one by one in order of priority, the acceleration points being cumulative points, and the control server storing attribute information of each user including the cumulative points of each user; skipping a first simulation request when detecting that an acceleration point of a first user corresponding to a first simulation request among the specified number of simulation request candidates is smaller than an acceleration parameter of the first simulation request, the acceleration parameter of the first simulation request being a point consumption rate set in the first simulation request; or When it is detected that the acceleration points of a second user corresponding to a second simulation request among the specified number of simulation request candidates are greater than an acceleration parameter of the second simulation request, the step of sending the second simulation request to a simulation server for simulation processing is used, wherein the acceleration parameter of the second simulation request is a point consumption rate set in the second simulation request.

[0012] In one possible embodiment, the simulation processing module further comprises: obtaining a target simulation server having the highest priority in an idle state from among the simulation servers, the priority of the simulation server being used to indicate the simulation processing performance of the simulation server; and sending the second simulation request to the target simulation server for processing.

[0013] In one possible embodiment, the simulation processing module further comprises: When detecting that the simulation process for the second simulation request has ended, the step of updating the second user's acceleration point to a difference between the second user's acceleration point and the acceleration parameter of the second simulation request is used.

[0014] In one possible embodiment, the device comprises: a simulation data acquisition module that, when detecting that a simulation process for a target simulation request candidate has been completed, acquires target simulation data corresponding to the target simulation request candidate in each target simulation server that has simulated the target simulation request candidate, the target simulation data including at least one of front server data and back server data, the front server data indicating a server that simulates the target simulation request candidate before acquiring the target simulation data, and the back server data indicating a server that simulates the target simulation request candidate after acquiring the target simulation data; and a simulation result sending module for splicing each of the target simulation data into the target simulation result and sending it to a target computing device, which is a device that sends the target simulation request candidates.

[0015] In one possible embodiment, the target simulation data further includes a circuit state of the target simulation server before performing a simulation operation on the target simulation request candidate, and a circuit state of the target simulation server after performing a simulation operation.

[0016] In yet another aspect, there is provided a computing device including a processor and a memory storing at least one instruction, at least one program, code set or instruction set that is loaded and executed by the processor to implement the above-described method for automatic parallel simulation of an integrated circuit.

[0017] In another aspect, there is provided a computer readable storage medium having stored thereon at least one instruction which, when loaded and executed by a processor, implements the above-described method for automated parallel simulation of an integrated circuit.

[0018] In yet another aspect, a computer program product is provided, as well as a computer program product or computer program comprising computer instructions stored on a computer readable storage medium, the computer instructions being read by a processor of a computing device from the computer readable storage medium and executed by the processor causing the computing device to perform the method for automated parallel simulation of an integrated circuit as described above. Effect of the Invention

[0019] The technical solutions according to the present application may include the following beneficial effects:

[0020] When a simulation needs to be performed on an integrated circuit, the computing device can send the integrated circuit structure to the simulation system via a circuit simulation request, at which time the control server in the simulation system adds the circuit simulation request to a first queuing queue as a simulation request candidate, and the control server further sorts the simulation request candidates in the queuing queue based on the remaining simulation time to obtain a second queuing queue, and the control server further performs a second sorting process on the simulation request candidates in the second queuing queue according to the magnitude of a preset acceleration parameter to obtain a target queuing queue, so that the simulation server simulates each simulation request candidate according to the priority indicated in the order.

[0021] Then, when the control server detects that the simulation process for the circuit simulation request is completed, it acquires the simulation data on which the simulation process for the circuit simulation request is executed from each simulation server, splices the simulation data, and obtains the final simulation result. In addition, each simulation data also indicates the simulation server executed before or after each simulation data, and the circuit state before or after each simulation data is obtained. Even if a part of the simulation data is lost in each simulation data, the control server can acquire the lost simulation initial condition and the circuit state at the end of the current simulation based on the circuit state at the end of the simulation stored in the data file of the previous simulation and the simulation initial condition stored in the data file of the next simulation, and can relocate the simulation server to perform simulation calculation based on the lost simulation initial condition and the circuit state at the end of the current simulation to obtain the currently lost part, thereby obtaining a complete simulation result without recalculating the entire simulation request from start to finish.

[0022] In the above embodiment, an intelligent queuing simulation is performed for each simulation request based on the performance of the simulation server, the demand of the target user, and the simulation execution time, and the resources of the simulation server are appropriately allocated and utilized. In addition, the simulation server is used to store and read simulation data files in a distributed manner, so that there is no need to transfer data files obtained by simulation calculation between different simulation servers. This makes the operation of the entire simulation server network smooth, ensures the execution speed of the simulation, and improves the efficiency of integrated circuit simulation. In order to more clearly describe the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly describe the drawings that need to be used in the description of the specific embodiments or the prior art. It is obvious that the drawings in the following description are some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without exerting creative efforts. [Brief description of the drawings]

[0023] [Figure 1] FIG. 1 is a schematic diagram of a simulation system according to one exemplary embodiment. [Diagram 2] 1 is a flow chart of a method for automatic parallel simulation of an integrated circuit according to one exemplary embodiment. [Diagram 3] 1 is a flow chart of a method for automatic parallel simulation of an integrated circuit according to one exemplary embodiment. [Figure 4] 1 is a block diagram of an automatic parallel simulation apparatus for an integrated circuit according to an exemplary embodiment; [Diagram 5] FIG. 2 is a schematic diagram of a computing device according to one exemplary embodiment of the present application. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0024] The technical solutions of the present application will be described below clearly and completely with reference to the drawings, but it is clear that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. Based on the embodiments of the present application, all other embodiments that a person skilled in the art can obtain without any creative efforts belong to the protection scope of the present application.

[0025] It should be understood that the term "show" in the embodiments of the present application may directly show, indirectly show, or show that there is an association relationship. For example, when A shows B, A may directly show B, e.g., B may be obtained through A, or A may indirectly show B, e.g., A shows C, B may be obtained through C, and it can also represent that there is an association relationship between A and B.

[0026] In describing the embodiments of the present application, the term "corresponding" may mean that there is a direct or indirect corresponding relationship between two things, or may mean that there is an association relationship between two things, such as a relationship between showing and being shown, or a relationship between making up and being made up, etc.

[0027] In the embodiments of the present application, "predefined" may be achieved by pre-storing in a device (including, for example, a terminal device and a network device) a corresponding code, table, or other form that can be used to indicate related information, and the present application is not limited to the specific embodiment.

[0028] 1 is a schematic diagram of a simulation system according to an exemplary embodiment. The simulation system includes a control server 110 and each simulation server 120. Here, data communication is performed between each simulation server 120 and the control server 110 via a communication network, which may be a wired network or a wireless network.

[0029] Optionally, the simulation system further includes a terminal 130, which may be a computing device used by an engineer to design an integrated circuit, and after the engineer designs the integrated circuit using the terminal 130, an application program installed on the terminal may generate a circuit simulation request from structural data corresponding to the integrated circuit, and send the circuit simulation request to a control server 110 of the simulation system, so that the control server 110 controls each simulation server to perform simulation processing for the circuit simulation request.

[0030] Optionally, an application program having a circuit design function is installed in the terminal 130, and the terminal 130 can execute the application program having the circuit design function to generate corresponding integrated circuit data when receiving a user-specified operation, but the embodiment of the present application is not limited thereto.

[0031] The terminal 130 may be a terminal device having a data transmission interface for receiving integrated circuit data generated by another computing device and constructing a circuit simulation request.

[0032] Optionally, the terminal 130 may be a mobile terminal such as a smartphone, tablet, or laptop, or may be a terminal such as a desktop computer or a projection computer, or may be a smart terminal having a data processing component, and the embodiments of the present application are not limited thereto.

[0033] The control server 110 or the simulation server 120 may be implemented as a single server, which may be a physical server or a cloud server. In one possible embodiment, the control server 110 is a background server of an application program in the terminal 130.

[0034] In one possible embodiment, after the simulation server completes the simulation operation corresponding to the (circuit) simulation request, the control server that allocates the simulation request retrieves the simulation result corresponding to the simulation request and sends it to the local computer of the engineer issuing the simulation request, specifically: A database is created in the server (control server) that allocates the simulation requests, which records the segment information of the simulation results corresponding to the simulation requests. For example, Simulation request A is executed multiple times on server executing simulation (i.e. simulation server) 1, server executing simulation 2, and server executing simulation 3, and the data file executed the first time on server executing simulation 1 is represented as A-1-1, the data file executed the second time on server executing simulation 1 is represented as A-1-2, the data file executed the first time on server executing simulation 2 is represented as A-2-1, the data file executed the first time on server executing simulation 3 is represented as A-3-1, the data file executed the second time on server executing simulation 3 is represented as A-3-2, etc. The server that allocates the simulation requests records the order in which all the simulation requests were executed on the corresponding servers that execute the simulations, and the order in which the simulations were executed, and each data file is stored on each server that executes the simulations; The server that allocates the simulation request reads each data file from the server that executes the simulation according to the recorded order, synthesizes them as the final simulation result, and transmits it to the local computer of the engineer issuing the simulation request.

[0035] Optionally, the server may be an independent physical server, a server cluster or a distributed system consisting of multiple physical servers, or a cloud server based on cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, big data and artificial intelligence platforms.

[0036] Optionally, the system may further include a management device that is connected to the server via a communication network and manages the system (e.g., manages a connection state between each module and the server). Optionally, the communication network is a wired network or a wireless network.

[0037] Optionally, the wireless or wired networks described above use standard communication technologies and / or protocols. The network is typically the Internet, but may be any other network, including but not limited to any combination of local area networks, metropolitan networks, wide area networks, mobile, wired or wireless networks, private networks, or virtual private networks. In some embodiments, technologies and / or formats including HyperText Markup Language, Extensible Markup Language, and the like are used to represent data exchanged over the network. Additionally, all or some links may be encrypted using conventional encryption technologies such as Secure Sockets Layer, Transport Layer Security, Virtual Private Networks, Internet Protocol Security, and the like. In another embodiment, customized and / or proprietary data communication technologies may be used to replace or supplement the above data communication technologies.

[0038] Fig. 2 is a flowchart of an automatic parallel simulation method for an integrated circuit according to one exemplary embodiment. The method is executed by a computer device that may be a control server in the simulation system shown in Fig. 1. As shown in Fig. 2, the automatic parallel simulation method for an integrated circuit may include the following steps 201 to 205.

[0039] Step 201: Obtain a circuit simulation request.

[0040] The circuit simulation request is used to request a simulation resource to simulate an integrated circuit structure.

[0041] In one possible embodiment, the circuit simulation request includes structural data for an integrated circuit.

[0042] That is, after obtaining the structure data of the integrated circuit, the terminal may generate a corresponding circuit simulation request based on the structure data of the integrated circuit and send it to a control server in the simulation system.

[0043] Step 202: Add this circuit simulation request to the first queuing queue as a simulation request candidate.

[0044] When the control server receives a circuit simulation request, it does not first perform a simulation process for the integrated circuit structure therein, but adds it to a first queuing queue to determine the simulation priority relationship between this circuit simulation request and other circuit simulation requests.

[0045] In one possible embodiment, the computing device adds each circuit simulation request to the first queuing queue as a candidate simulation request according to the acquisition time of each circuit simulation request, i.e., a circuit simulation request acquired first is earlier in the first queuing queue and a circuit simulation request acquired later is later in the first queuing queue.

[0046] Step 203: Based on the remaining simulation time of each simulation request candidate in the first queuing queue, a first sorting process is performed on each simulation request candidate in the queuing queue to obtain a second queuing queue.

[0047] The computer device, i.e., the control server of FIG. 1, needs to select simulation request candidates to be pushed to the simulation server for simulation in the next simulation period, and at this time, the control server calculates the remaining simulation time of each simulation request candidate in the obtained first queuing queue, and performs a first sorting process on each simulation request candidate according to the remaining simulation time of the simulation request candidate to obtain a second queuing queue.

[0048] In one possible embodiment of the present application, the computer device adjusts the order of each simulation request candidate in the first queuing queue according to the size of the remaining simulation time to obtain a second queuing queue.

[0049] Here, the process of adjusting the order may be to compare the relationship in size of the remaining simulation time between two adjacent simulation request candidates one by one until the remaining simulation time of the earlier simulation request candidate among the two adjacent simulation request candidates becomes equal to or less than the remaining simulation time of the later simulation request candidate.

[0050] In one possible embodiment, the remaining simulation time for each simulation request candidate in this first queuing queue may be simulated by the computing device based on the number of circuit structures and parameter values ​​of each simulation request candidate.

[0051] For example, if the circuit structure in the simulation request candidate is complex and has a large number of parameter values, the functions that the simulation server needs to fit when simulating this circuit structure will also be complex, and the time it takes to make a simulation request will also be long.

[0052] At this time, the remaining simulation time of each simulation request candidate represents the predicted time required to process that simulation request candidate. By processing the simulation request candidate with the shortest remaining simulation time first, the simulation server can process more simulation requests within the specified time, and it is possible to avoid delaying the processing of other circuit simulation requests due to one or more complex circuit simulation requests having many parameters.

[0053] In another possible embodiment, the remaining simulation time is used to indicate the remaining processing progress of candidate simulation requests whose simulation has started before the target processing period.

[0054] In the simulation system shown in FIG. 1, each simulation server processes each simulation request candidate every cycle, and after completing one cycle of calculation, each simulation server reallocates computational resources to process simulation request candidates that remain in the queuing queue, have not been processed, or have not been started.

[0055] At this time, after the execution of a simulation task for a certain cycle is completed and before the simulation task for the next cycle is started (i.e., before the target processing cycle), the computer device collects statistics on simulation request candidates in the queuing queue at that time for which processing has not been completed or processing has not been started, obtains simulation request candidates for which processing has already been started but not completed, and calculates the remaining simulation time required to process the remaining progress from the processing progress and processing time in the previous cycle.

[0056] At this time, when sorting the simulation request candidates for which the simulation process has been started but not completed according to the remaining simulation time, the computer device puts the simulation request candidates with the longest remaining simulation time at the end of the sorting order.

[0057] A long remaining simulation time means that even if a simulation request has gone through at least one cycle of candidate simulation requests, it needs to be moved to a later position because it requires a lot of simulation resources for simulation processing and may delay the processing progress of other simulation requests.

[0058] In one possible embodiment, the computing device determines the remaining simulation time of a newly started candidate simulation request obtained within the target processing period to be zero.

[0059] At this time, when performing a sorting process on the first queuing queue, the computer device moves the unprocessed simulation request candidates to the front so that the unprocessed simulation request candidates as a whole are preferentially processed.

[0060] In one possible embodiment, the computing device halves the remaining simulation time of simulation request candidates that have not undergone simulation processing within the previous period.

[0061] A simulation request candidate that was not simulated during the previous cycle can have the following two forms. One form is that there is no time to perform simulation processing for this simulation request candidate, or this simulation request candidate was added to the queuing queue during the previous cycle but was not processed. In this case, the remaining simulation time must be set to 0 during the processing cycle in which the control server retrieved this simulation request candidate, so even if the remaining simulation time is halved, it remains 0.

[0062] In the other form, if this simulation request candidate was sent to the simulation server for simulation processing two cycles ago, but was not processed because the processing was not completed and it was not added to the queuing queue within the previous cycle, then the remaining simulation time of this simulation request candidate is halved.

[0063] In other words, when a simulation request candidate is not processed for one or more cycles, in order to prevent the predicted processing time from being too long and the simulation request candidate being left unattended for a long time, the remaining simulation time is halved, thereby increasing the priority of the simulation request candidate and enabling the control server to send even the simulation request candidate with the long processing time to the simulation server for processing.

[0064] Step 204: A second sorting process is performed on the second queuing queue according to the magnitude of the acceleration parameter of each simulation request candidate in the second queuing queue to obtain a target queuing queue.

[0065] The computer device performs a first sorting process on each simulation request candidate in the first queuing queue to obtain a second queuing queue. At this time, each simulation request candidate in the second queuing queue takes into consideration the simulation time required for processing the simulation request candidate. In practical applications, each simulation request candidate has a theoretical priority, that is, some integrated circuit structures in the simulation request candidates need to consume a lot of resources but are very important and the simulation results are urgently needed. At this time, the computer device only needs to set a larger acceleration parameter when generating the simulation request candidates, so that the simulation server can prioritize the simulation processing of these simulation request candidates.

[0066] In one possible embodiment, an authority value of a target user corresponding to each of the simulation request candidates is obtained, and the authority value of the target user is set as an acceleration parameter of each of the simulation request candidates.

[0067] In order to further determine the importance of each simulation request candidate, a corresponding authority value may be preset in the control server for each user who is permitted to submit a simulation request candidate, and a larger authority value indicates that the user has a higher authority. When a target user requests acceleration processing in a simulation request candidate, the control server determines the authority value of each target user as an acceleration parameter of the simulation request candidate, and realizes the order adjustment of each simulation request candidate in the queuing queue by comparing the execution priority of each simulation request candidate according to the acceleration parameter of each simulation request candidate.

[0068] In one possible embodiment, a second sorting process is performed on the second queuing queue according to the magnitude of the acceleration parameter of each simulation request candidate in the second queuing queue to obtain a third queuing queue, and the acceleration points of each target user corresponding to each simulation request candidate are obtained.Of the simulation request candidates in the third queuing queue, those whose corresponding target user acceleration points are greater than the acceleration parameter are constructed as the target queuing queue according to the magnitude of the acceleration parameter.

[0069] In this case, the acceleration parameters in the candidate simulation request can be set by a user via a computing device during generation of the candidate simulation request.

[0070] After obtaining the magnitude of the acceleration parameter of each simulation request candidate in the second queuing queue, the control server needs to compare it with the acceleration point of each target user stored in the control server, i.e., compare whether the magnitude of the acceleration parameter set by the target user exceeds the allowable range of that target user.

[0071] When it is detected that the acceleration parameter of the simulation request candidate is larger than the acceleration point of the target user of the simulation request candidate, it is indicated that the acceleration parameter of the simulation request candidate exceeds the allowable range of the target user, in which case the simulation request candidate is ignored and no simulation processing is performed within the current processing period of the simulation server.

[0072] Therefore, the control server can construct simulation request candidates whose corresponding target users' acceleration points are greater than this acceleration parameter as a target queuing queue indicating the simulation processing priority of each simulation request candidate within the current processing period.

[0073] Step 205: According to the priority indicated by the target queuing queue, each simulation server performs simulation processing for each of the simulation request candidates within a target processing period.

[0074] In one possible embodiment, each simulation server in the present embodiment is prioritized according to performance, with the more highly performing simulation servers having a higher priority.

[0075] At this time, after obtaining the target queuing queue, the control server extracts the simulation request candidates one by one according to the priority indicated by the target queuing queue, assigns them to an idle simulation server according to the simulation server priority, performs simulation processing, and obtains simulation results corresponding to these simulation request candidates.

[0076] For example, when a simulation request candidate is retrieved from the target queuing queue, the control server detects the status of each simulation server, and selects the simulation server with the highest priority (i.e., the highest performance) among the idle simulation servers at that time as the server that will simulate and process this simulation request candidate.

[0077] Therefore, each simulation request candidate is read from the target queuing queue according to priority, and since the lower the priority and the later it is retrieved, the lower the processing performance of the assigned simulation server will theoretically be, each simulation request candidate is assigned to a simulation server with a different performance according to priority, and the simulation operation can be executed in the target processing cycle (i.e., the current processing cycle), thereby enabling rational use of resources.

[0078] The control server sorts each simulation request candidate in the queuing queue based on the remaining simulation time and the magnitude of the acceleration parameter, forms a target queuing queue, and then, when processing the simulation request candidates in the target queuing queue, performs an intelligent queuing simulation for each simulation request based on the performance of the simulation server, the demand of the target user, and the simulation execution time, etc., and appropriately allocates and utilizes the resources of the simulation server.

[0079] As described above, when a simulation needs to be performed on an integrated circuit, the computer device can send the integrated circuit structure to the simulation system through a circuit simulation request, and at this time, the control server in the simulation system adds the circuit simulation request to a first queuing queue as a simulation request candidate, and the control server further sorts the started simulation request candidates in the queuing queue based on the remaining simulation time to obtain a second queuing queue, and the control server further performs a second sorting process on the simulation request candidates in the second queuing queue according to the magnitude of the preset acceleration parameter to obtain a target queuing queue, so that the simulation server simulates each simulation request candidate according to the priority indicated in the order. In the above embodiment, an intelligent queuing simulation is performed on each simulation request based on the performance of the simulation server, the demand of the target user, and the time of simulation execution, etc., and the resources of the simulation server are appropriately allocated and utilized, thereby improving the efficiency of the integrated circuit simulation.

[0080] 3 is a flowchart of an automatic parallel simulation method for an integrated circuit according to one exemplary embodiment. The method is performed by a computer device that may be a control server in the simulation system shown in FIG 1. As shown in FIG 3, the automatic parallel simulation method for an integrated circuit may include the following steps 301 to 304.

[0081] Step 301: Obtain a circuit simulation request.

[0082] In the embodiment of the present application, after an engineer completes the design of a circuit structure of an integrated circuit, he submits a simulation request generated by the circuit structure to a control server in a simulation system.

[0083] In one possible embodiment of the present application, the simulation system includes one server (the control server in FIG. 1) for allocating simulation requests, and multiple servers (the simulation servers in FIG. 1) for executing simulations. Also, the multiple servers for executing simulations are sorted in descending order of performance, i.e., the first server at the head of the queue of the multiple servers for executing simulations has the highest performance, and the last server at the end has the lowest performance.

[0084] Step 302: Add this circuit simulation request to the first queuing queue as a simulation request candidate.

[0085] In one possible embodiment, the control server may also perform a duplicate check analysis process on the circuit simulation request before adding the circuit simulation request to the first queuing queue as a candidate simulation request.

[0086] The control server performs a duplicate check analysis on the circuit structure by analyzing the netlist file of the circuit structure to determine whether the circuit structure or a circuit structure similar to the circuit structure has submitted a simulation request.

[0087] The netlist file is mainly divided into four parts, including component types, component parameter values, connection relationships between components, and simulation conditions. By comparing each part of the netlist file of a circuit structure that has previously submitted a simulation request with each part of the netlist file of this circuit structure, it is possible to determine whether this circuit structure or a circuit structure similar to this circuit structure has submitted a simulation request; When a circuit structure submits a simulation request, search for the simulation result of this circuit structure in the cache of completed simulations, if the simulation result is found in the cache of completed simulations, directly retrieve and send the simulation result to the engineer's computing device, if the simulation result is not found in the cache of completed simulations, mark the number of simulation iterations as indicating that the cache of simulation results has been cleaned up, and add the simulation request of this circuit structure to the queuing queue, if the previously submitted circuit structure is being simulated, ignore the request, and inform the engineer that the previously submitted circuit structure is being simulated.

[0088] Step 303: Based on the remaining simulation time of each simulation request candidate in the first queuing queue, a first sorting process is performed on each simulation request candidate in the queuing queue to obtain a second queuing queue.

[0089] In one possible embodiment of the present application, the computing device calculates an average simulation speed in a previous period for each executed simulation request (a simulation request that has already been executed in the simulation server), and estimates the remaining simulation time from the simulation speed and the current progress; Sets the estimated remaining simulation time of a newly started simulation request (a simulation request that has just been added to the queuing queue to be simulated on the simulation server) to 0.

[0090] Note that the estimated remaining simulation time may not match the actual remaining simulation time, and the actual simulation speed changes significantly depending on the change in the circuit state, so it is not possible to obtain an accurate actual remaining simulation time. Therefore, in this application, the simulation queue is sorted based on the estimated simulation time.

[0091] In one possible embodiment, the computing device performs an up calculation of the estimated remaining simulation time of the simulation requests that were not executed in the previous cycle (which may be the estimated remaining simulation time calculated in a previous executed cycle), i.e., the up calculation reduces the estimated remaining simulation time of the simulation requests that were not executed in the previous cycle, thereby ensuring that the execution order of the simulation requests that were not executed in the previous cycle is advanced in the current cycle.

[0092] The pull operation can be any algorithm that can be implemented, and one optional algorithm is to halve the estimated remaining simulation time of the simulation request that was not executed in the previous cycle, and make the halved estimated remaining simulation time the estimated remaining time of this simulation request in the current cycle.

[0093] The computing device sorts all simulation requests in the queuing queue in ascending order based on the estimated remaining time.

[0094] Step 304: A second sorting process is performed on the second queuing queue according to the magnitude of the acceleration parameter of each simulation request candidate in the second queuing queue to obtain a target queuing queue.

[0095] In an embodiment of the present application, the acceleration parameter may be set as a point consumption rate of the acceleration points corresponding to the target user.

[0096] In one possible embodiment, there is attribute information corresponding to each requester (i.e., a target user such as an engineer) in the control server, and regardless of whether the requester has a simulation request currently started, in the control server, each requester acquires points per unit time (one period), and the accumulated points O and point acquisition speed P of each requester are stored in the attribute information of the control server; Here, the points acquired per unit time (one period) can be set according to the actual situation.

[0097] When a target user initiates a simulation request, the target user can set a point consumption speed Q (ie, an acceleration parameter) in the simulation request, which indicates how many points are consumed in a unit time to use a simulation resource.

[0098] For example, the value of the point consumption rate Q may follow the following rules: (1) The setting range of Q must be greater than or equal to P, and the default is twice P. (2) The requestor (engineer) can also set the point consumption rate Q by himself / herself according to his / her requirements. Specifically, the requestor (engineer) issues a simulation request to the control server on his / her local computer and at the same time provides the point consumption rate Q that he / she has set by himself / herself. (3) If the simulation request is not for repeating a simulation, the number of simulation requests M is counted as 1.

[0099] If the simulation request is for repeating a simulation, the number of simulation requests M is counted as the number of times that a specific simulation has been submitted.

[0100] If the point consumption rate Q corresponding to the simulation request closest to the head of the queuing queue is slower than the point consumption rate Q corresponding to the next simulation request, swap the positions of these two simulation requests in the queuing queue; If the point consumption speed Q corresponding to the simulation request closest to the head of the queuing queue is equal to or greater than the point consumption speed Q corresponding to the next simulation request, no operation is performed; Repeat the operation until the point consumption speed Q corresponding to the simulation request closest to the head of the queuing queue is no longer slower than the point consumption speed Q corresponding to the next simulation request; The point consumption speed Q can be set by the requester by itself. Therefore, when a requester (engineer) thinks that his / her circuit only needs to verify some functions, or due to project progress or other reasons, he / she needs to perform simulation on the circuit as soon as possible, the requester (engineer) can set a fast point consumption speed Q by himself / herself, so that the corresponding simulation request candidate has a fast point consumption speed Q (i.e., a larger acceleration parameter), thereby allowing the simulation request candidate to be quickly queued to the front of the target queuing queue, and reducing the simulation queuing time at the expense of the simulation execution time.

[0101] Step 305: According to the priority indicated by the target queuing queue, a designated number of simulation request candidates are extracted, and acceleration point detection is performed on the designated number of simulation request candidates one by one in order of priority.

[0102] After obtaining the target queuing queue through the above steps, a specified number of simulation request candidates can be extracted and acceleration point detection can be performed one by one. For example, the specified number can be determined according to the number of simulation servers, or can be determined according to the number of simulation servers currently in an idle state.

[0103] Step 306A: If detecting that the acceleration point of the first user corresponding to a first simulation request among the specified number of simulation requests is less than the acceleration parameter of the first simulation request, skip the first simulation request.

[0104] Optionally, the acceleration points are the accumulated points O of the first user (i.e., a requestor), and the acceleration parameter of the first simulation request is a point consumption rate Q corresponding to the simulation request submitted to the first user.

[0105] In the embodiment of the present application, the control server sequentially retrieves simulation requests from the head of the queuing queue, and compares the point consumption speed Q corresponding to the simulation request with the accumulated points O corresponding to the request source corresponding to the simulation request; If the point consumption speed Q is greater than the accumulated points O, no operation is performed on this simulation request, and comparison with the next simulation request continues.

[0106] Step 306B: If it is detected that the acceleration point of the second user corresponding to a second simulation request among the specified number of simulation requests is greater than the acceleration parameter of the second simulation request, then send the second simulation request to the simulation server for simulation processing.

[0107] In one possible embodiment, according to the priority indicated by the target queuing queue, a target simulation server that is idle and has the highest priority is obtained among the simulation servers, and the second simulation request is sent to the target simulation server for processing.

[0108] In one possible embodiment, when it is detected that the simulation process for the second simulation request has ended, the difference between the acceleration point of the second user and the acceleration parameter of the second simulation request is updated to the acceleration point of the second user.

[0109] For example, the process of processing this simulation request candidate is as shown in the following steps. 1) In the generated queuing queue, the control server sequentially takes out simulation requests from the top of the queuing queue and compares the point consumption rate Q corresponding to this simulation request with the accumulated points O corresponding to the request source corresponding to this simulation request. 2) If the point consumption speed Q is less than or equal to the cumulative points O, the server for allocating the simulation request searches from the top of the simulation server queue for the first server that has not been assigned a simulation request task (i.e., the simulation server with the highest priority and the highest processing capacity), allocates the simulation request retrieved this time to this simulation server for execution, calculates OM*Q, and sets the result as the new cumulative points O. 3) The operation is repeated until all simulation requests remaining in the simulation request queue satisfy the condition that the point consumption speed Q is equal to or less than the accumulated points O, or until all simulation servers have been assigned simulation request tasks.

[0110] In one possible embodiment, if the server is not fully scheduled to run a simulation (i.e., the simulation server is idle) and there are unexecuted simulation requests in the target queuing queue of simulation requests, the following operations are performed:

[0111] Sort all remaining simulation requests in the target queuing queue in descending order of cumulative points O of the corresponding requesters (engineers), The simulation requests are taken out one by one from the top of the sorted queue. From the top of the servers for executing the simulation, the first server to which a simulation request task has not been assigned is searched for, the simulation request candidate extracted this time is sent to the simulation server for execution, OM*Q is calculated, and the result is regarded as the new cumulative point O.

[0112] In one possible embodiment, if there is an idle simulation server and there are no unassigned simulation requests in the target queuing queue for simulation requests, the following operations are performed.

[0113] The control server finds the last unallocated simulation request, and calculates the difference R between the point consumption rate Q and the point acquisition rate P corresponding to this simulation request; The latest cumulative point O is calculated by adding the difference R to the cumulative points O corresponding to the request sources corresponding to all simulation requests that have not been assigned within the current period.

[0114] In one possible embodiment, a simulation server may quickly complete a simulation operation when processing a candidate simulation request, without having to spend an entire processing cycle, at which point the simulation server becomes idle again.

[0115] At this time, the control server can retrieve the calculation results of the simulation server that has completed the simulation calculation, re-determine the simulation request candidates in the target queuing queue, and transmit them to this simulation server.

[0116] That is, when the current cycle ends, once the execution of a simulation request on one or several simulation servers is completed, the control server retrieves the simulation results corresponding to this simulation request in real time.

[0117] If the execution of a simulation request in one or some simulation servers is completed within the current period, the control server can retrieve the simulation request and the corresponding simulation result after the current period ends, and can also schedule a new simulation request in real time for the idle simulation server after obtaining the simulation request and the corresponding simulation result in real time. The specific steps of scheduling a new simulation request in real time are as follows: (1) Determine whether there are any remaining simulation requests that have not been assigned to the queuing queue of the simulation requests. If there are no remaining simulation requests, perform no operation on the idle simulation server. If there are remaining simulation requests, sort all the simulation requests in the queuing queue of the remaining simulation requests in ascending order based on the estimated remaining time. (2) Compare the point consumption rates Q corresponding to any two adjacent simulation requests in the queuing queue sorted above. Specifically, If the point consumption rate Q corresponding to the simulation request closest to the head of the queuing queue is slower than the point consumption rate Q corresponding to the next simulation request, swap the positions of these two simulation requests in the queuing queue; If the point consumption speed Q corresponding to the simulation request closest to the head of the queuing queue is equal to or greater than the point consumption speed Q corresponding to the next simulation request, no operation is performed; The operation is repeated until the point consumption rate Q corresponding to the simulation request closest to the head of the queuing queue is no longer slower than the point consumption rate Q corresponding to the next simulation request.

[0118] In the queuing queue generated above, the simulation requests are sequentially taken out from the head of the queuing queue, and the point consumption speed Q corresponding to the simulation request is compared with the accumulated points O corresponding to the request source corresponding to the simulation request; If the point consumption speed Q is less than or equal to the cumulative points O, the server for allocating the simulation request searches for the first server that has not been assigned a simulation request task from the top of the queue of servers for executing the simulation, allocates the simulation request retrieved this time to that server for execution, calculates OM*Q, and sets the result as the new cumulative points O. If the point consumption speed Q is greater than the accumulated points O, no operation is performed on this simulation request, and the comparison of the next simulation request continues; The operation is repeated until all simulation requests remaining in the simulation request queue satisfy the condition that the point consumption rate Q is equal to or less than the accumulated points O, or until all simulation servers for executing the simulations are assigned simulation request tasks.

[0119] In one possible embodiment, after the above operations for each simulation request candidate are completed, it is detected whether all the simulation servers are in an operational state.

[0120] If the idle servers for running the simulations have not yet been fully allocated and there are still unallocated simulation requests in the queuing queue for the remaining simulation requests, sort the remaining simulation requests in descending order of the cumulative points O of the corresponding request origins (target users); The simulation requests are taken out one by one from the top of the sorted queue. The first server to which a simulation request task has not been assigned is searched from the top of the simulation servers, the currently extracted simulation request is assigned to this server for execution, OM*Q is calculated, and the result is regarded as a new cumulative point O.

[0121] In one possible embodiment, when a period ends, when the execution of a simulation request is completed, the control server retrieves the simulation results corresponding to the simulation request in real time and transmits the simulation results to a local computer of the engineer issuing the simulation request; If the execution of a simulation request is completed within a certain period, the control server can retrieve the simulation results corresponding to this simulation request after the end of the current period and send them to the local computer of the engineer who issued the simulation request, and can also retrieve the simulation results corresponding to this simulation request in real time and send them to the local computer of the engineer who issued the simulation request.

[0122] In one possible embodiment, upon detecting that the simulation process for the target simulation request candidate is completed, obtain target simulation data corresponding to the target simulation request candidate in each target simulation server that simulated the target simulation request candidate, splice each target simulation data into the target simulation result, and send it to the target computing device, which is the device that sends the target simulation request candidate.

[0123] This target simulation data includes at least one of front server data and back server data, where the front server data is for indicating a server that simulates the target simulation request candidate before obtaining the target simulation data, and the back server data is for indicating a server that simulates the target simulation request candidate after obtaining the target simulation data.

[0124] That is, in one possible embodiment of the embodiment of the present application, the control server has a database for recording simulation requests and corresponding segment information of simulation results (optionally, a database server for storing the database can be provided separately). Meanwhile, in order to prevent unexpected situations in the control server where the database is located, the simulation server where the previous data file is located (front server data) and the simulation server where the next data file is located (back server data) are recorded in each data file (i.e., simulation data obtained by simulation). For example, If the data file before A-2-2 is A-1-2 and the next data file is A-3-1, the position A-1-2 of the previous data file is recorded at the beginning of A-2-2, and the position A-3-1 of the next data file is recorded at the end of A-2-2. At this time, each position information indicates the ID of each simulation server.

[0125] Therefore, the local computer of the engineer issuing the simulation request can access all the simulation servers, obtain the complete execution sequence of the simulation based on the data files, and obtain the complete simulation results for sending to the local computer.

[0126] In one possible embodiment, the target simulation data further includes a circuit state of the target simulation server before performing a simulation operation on the target simulation request candidate, and a circuit state of the target simulation server after performing the simulation operation.

[0127] In other words, in order to prevent the loss of a part of the data file due to a failure of the simulation server in which a certain part of the data file exists, resulting in an incomplete result of the entire simulation, the initial conditions of the current simulation (i.e., the initial circuit state at the end of the previous simulation) and the circuit state after the current simulation operation (i.e., the initial conditions of the next simulation) are stored in all data files at this time, When a failure occurs in the server used for the current simulation, and the control server on which the database is located operates normally, after the data file of the current simulation is lost, the control server determines which simulation server the data file of the previous simulation and the data file of the next simulation are located on, and thereby obtains the lost simulation initial conditions of the current simulation and the circuit state after the simulation operation based on the circuit state at the end of the simulation stored in the data file of the previous simulation and the simulation initial conditions stored in the data file of the next simulation. Based on the lost simulation initial conditions of the current simulation and the circuit state after the simulation operation, the simulation server can be relocated to perform simulation calculation to obtain the currently lost part, thereby obtaining a complete simulation result without recalculating the entire simulation request from start to finish.

[0128] When the simulation server used for the current simulation fails and the control server also fails, after the data file of the current simulation is lost, the local computer of the engineer who issues the simulation request can access all simulation servers and, according to the simulation execution order of all data files, find which simulation server the data file of the previous simulation of the lost current simulation and the data file of the next simulation are located on, so as to obtain the simulation initial conditions and the circuit state after the simulation operation of the lost current simulation based on the circuit state after the simulation operation stored in the data file of the previous simulation and the simulation initial conditions stored in the data file of the next simulation, and perform the simulation calculation again on the local computer based on the simulation initial conditions and the circuit state after the simulation operation of the lost current simulation to obtain the currently lost part, so as to obtain a complete simulation result without recalculating the entire simulation request from start to finish.

[0129] The simulation system deployed through the above scheme can quickly and effectively obtain complete simulation results even if a server fails. By using the simulation servers to store and read simulation data files in a distributed manner, data files obtained by simulation calculations do not need to be transferred between different simulation servers, so the operation of the entire simulation server network is smooth, the simulation execution speed is ensured, and the simulation efficiency is improved.

[0130] As described above, when a simulation needs to be performed on an integrated circuit, the computer device can send the integrated circuit structure to the simulation system through a circuit simulation request, and at this time, the control server in the simulation system adds the circuit simulation request to the first queuing queue as a simulation request candidate, and the control server further sorts the started simulation request candidates in the queuing queue based on the remaining simulation time to obtain a second queuing queue, and the control server further performs a second sorting process on the simulation request candidates in the second queuing queue according to the magnitude of the preset acceleration parameter to obtain a target queuing queue, so that the simulation server simulates each simulation request candidate according to the priority indicated in the order. In the above embodiment, an intelligent queuing simulation is performed for each simulation request based on the performance of the simulation server, the demand of the target user, and the simulation execution time, and the resources of the simulation server are appropriately allocated and utilized, thereby encouraging the requester to submit a good quality simulation request instead of repeatedly using the simulation trial and error of the server to design, and also preventing a simulation request requiring a relatively long time from occupying good quality server resources for a long time, thereby improving the efficiency of the integrated circuit simulation.

[0131] FIG. 4 is a block diagram of an automatic parallel simulation apparatus for an integrated circuit according to an exemplary embodiment. a simulation request acquisition module 401 for acquiring a circuit simulation request for requesting a simulation resource to simulate an integrated circuit structure; a first queue acquisition module 402 for adding the circuit simulation request to a first queuing queue as a simulation request candidate; a second queue acquisition module 403 for performing a first sorting process on each simulation request candidate in the first queuing queue based on the remaining simulation time of each simulation request candidate in the first queuing queue to obtain a second queuing queue; a target queue acquisition module 404 for performing a second sorting process on the second queuing queue according to the magnitude of the acceleration parameter of each simulation request candidate in the second queuing queue to obtain a target queuing queue; a simulation processing module 405 for performing simulation processing for each of the simulation request candidates by each of the simulation servers within a target processing period according to the priority indicated by the target queuing queue.

[0132] In one possible embodiment, the remaining simulation time is used to indicate remaining processing progress of candidate simulation requests whose simulation has started before the target processing period; The apparatus further includes a remaining time determining module that determines a remaining simulation time of a newly started candidate simulation request obtained within a target processing period to be zero.

[0133] In one possible embodiment, the simulation processing module further comprises: A step of extracting a designated number of simulation request candidates according to the priority indicated by the target queuing queue, and performing acceleration point detection for the designated number of simulation request candidates one by one in order of priority; skipping the first simulation request when detecting that an acceleration point of a first user corresponding to a first simulation request among the specified number of simulation request candidates is smaller than an acceleration parameter of the first simulation request; or When it is detected that the acceleration point of a second user corresponding to a second simulation request among the specified number of simulation request candidates is greater than the acceleration parameter of the second simulation request, the step of sending the second simulation request to a simulation server for simulation processing is used.

[0134] In one possible embodiment, the simulation processing module further comprises: obtaining a target simulation server having the highest priority in an idle state from among the simulation servers, the priority of the simulation server being used to indicate the simulation processing performance of the simulation server; and sending the second simulation request to the target simulation server for processing.

[0135] In one possible embodiment, the simulation processing module further comprises: When detecting that the simulation process for the second simulation request has ended, the step of updating the second user's acceleration point to a difference between the second user's acceleration point and the acceleration parameter of the second simulation request is used.

[0136] In one possible embodiment, the device comprises: a simulation data acquisition module that, when detecting that a simulation process for a target simulation request candidate has been completed, acquires target simulation data corresponding to the target simulation request candidate in each target simulation server that has simulated the target simulation request candidate, the target simulation data including at least one of front server data and back server data, the front server data indicating a server that simulates the target simulation request candidate before acquiring the target simulation data, and the back server data indicating a server that simulates the target simulation request candidate after acquiring the target simulation data; and a simulation result sending module for splicing each of the target simulation data into the target simulation result and sending it to a target computing device, which is a device that sends the target simulation request candidates.

[0137] In one possible embodiment, the target simulation data further includes a circuit state of the target simulation server before performing a simulation operation on the target simulation request candidate, and a circuit state of the target simulation server after performing a simulation operation.

[0138] As described above, when a simulation needs to be performed on an integrated circuit, the computer device can send the integrated circuit structure to the simulation system through a circuit simulation request, and at this time, the control server in the simulation system adds the circuit simulation request to a first queuing queue as a simulation request candidate, and the control server further sorts the started simulation request candidates in the queuing queue based on the remaining simulation time to obtain a second queuing queue, and the control server further performs a second sorting process on the simulation request candidates in the second queuing queue according to the magnitude of the preset acceleration parameter to obtain a target queuing queue, so that the simulation server simulates each simulation request candidate according to the priority indicated in the order. In the above embodiment, an intelligent queuing simulation is performed on each simulation request based on the performance of the simulation server, the demand of the target user, and the time of simulation execution, etc., and the resources of the simulation server are appropriately allocated and utilized, thereby improving the efficiency of the integrated circuit simulation.

[0139] FIG. 5 is a schematic diagram of a computing device according to one exemplary embodiment of the present application, the computing device including a processor and a memory for storing a computer program that, when executed by the processor, implements the above method.

[0140] Here, the processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or other chips, or a combination of the above chips.

[0141] The memory, as a non-transitory computer-readable storage medium, can be used to store modules such as non-transitory software programs, non-transitory computer-executable programs, and program instructions / modules corresponding to the methods in the embodiments of the present application. The processor executes the non-transitory software programs, instructions, and modules stored in the memory to perform various functional applications and data processing of the processor, i.e., to realize the methods in the above method embodiments.

[0142] The memory may include a program storage area capable of storing an operating system, an application program required for at least one function, and a data storage area capable of storing data created by the processor, etc. Additionally, the memory may include high-speed random access memory, and may also include non-transient memory, such as at least one magnetic disk storage device, flash memory device, or other non-transient solid-state memory device. In some embodiments, the memory may optionally include memory located remotely with respect to the processor, which may be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, a corporate intranet, a local area network, a mobile communication network, and combinations thereof.

[0143] In one exemplary embodiment, there is further provided a computer readable storage medium having stored thereon at least one computer program which, when loaded and executed by a processor, performs all or part of the steps of the method. For example, the computer readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a Compact Disc Read-Only Memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0144] Those skilled in the art may easily conceive other embodiments of the present application after studying the specification and practicing the examples of the invention disclosed herein. The present application is intended to cover any modifications, uses or adaptations of the present application, including common knowledge or customary technical means in the art not disclosed herein, that follow the general principles of the present application. The specification and examples are to be treated as exemplary only, with the true scope and spirit of the present application being indicated by the following claims.

[0145] It should be understood that the present application is not limited to the specific structures described above and illustrated in the drawings, and various modifications and changes can be made thereto without departing from the scope thereof, which is limited only by the appended claims.

Claims

1. A method for automatic parallel simulation of an integrated circuit, comprising: used in a control server in a simulation system further including each simulation server, obtaining a circuit simulation request for requesting a simulation resource to simulate an integrated circuit structure; adding the circuit simulation request to a first queuing queue as a simulation request candidate; performing a first sorting process on each simulation request candidate in the first queuing queue based on a remaining simulation time of each simulation request candidate in the first queuing queue to obtain a second queuing queue; performing a second sorting process on the second queuing queue according to the magnitude of an acceleration parameter of each simulation request candidate in the second queuing queue to obtain a target queuing queue; and performing simulation processing for each of the simulation request candidates by each of the simulation servers within a target processing period in accordance with the priority indicated by the target queuing queue.

2. The remaining simulation time is used to indicate the remaining processing progress of the candidate simulation requests whose simulations are started before the target processing period; before performing a first sorting process on each simulation request candidate in the first queuing queue based on a remaining simulation time of each simulation request candidate in the first queuing queue; 2. The method of claim 1, further comprising the step of determining a remaining simulation time of a newly started simulation request candidate obtained within a target processing period to be zero.

3. performing a simulation process on each of the simulation request candidates by each of the simulation servers according to a priority indicated by the target queuing queue, A step of extracting a designated number of simulation request candidates according to the priority indicated by the target queuing queue, and performing acceleration point detection for the designated number of simulation request candidates one by one in order of priority, the acceleration points being cumulative points, and the control server storing attribute information of each user including the cumulative points of each user; skipping the first simulation request when detecting that the acceleration points of the first user corresponding to a first simulation request among the specified number of simulation request candidates are smaller than an acceleration parameter of the first simulation request, wherein the acceleration parameter of the first simulation request is a point consumption rate set in the first simulation request; or 3. The method of claim 2, further comprising: when detecting that the acceleration points of a second user corresponding to a second simulation request among the specified number of simulation request candidates are greater than an acceleration parameter of the second simulation request, sending the second simulation request to a simulation server for simulation processing, wherein the acceleration parameter of the second simulation request is a point consumption rate set in the second simulation request.

4. The step of transmitting the second simulation request to a simulation server for simulation processing comprises: obtaining a target simulation server having the highest priority in an idle state among the simulation servers, the priority of the simulation server being used to indicate the simulation processing performance of the simulation server; 4. The method of claim 3, further comprising the step of: sending the second simulation request to the target simulation server for processing.

5. 5. The method of claim 4, further comprising the step of updating the second user's acceleration points to a difference between the second user's acceleration points and the acceleration parameter of the second simulation request when detecting that the simulation process for the second simulation request has ended.

6. a step of acquiring target simulation data corresponding to the target simulation request candidate in each target simulation server which simulated the target simulation request candidate when it is detected that a simulation process for the target simulation request candidate has been completed, the target simulation data including at least one of front server data and back server data, the front server data being for indicating a server which simulates the target simulation request candidate before acquiring the target simulation data, and the back server data being for indicating a server which simulates the target simulation request candidate after acquiring the target simulation data; The method of any one of claims 1 to 5, further comprising the step of splicing each of the target simulation data as a result of the target simulation and transmitting the result to a target computer device, which is a device that transmits the target simulation request candidates.

7. 7. The method of claim 6, wherein the target simulation data further includes a circuit state of the target simulation server before performing a simulation operation on the target simulation request candidate, and a circuit state of the target simulation server after performing a simulation operation on the target simulation request candidate.

8. An automatic parallel simulation apparatus for an integrated circuit, comprising: a simulation request acquisition module for acquiring a circuit simulation request for requesting a simulation resource to simulate an integrated circuit structure; a first queue acquisition module for adding the circuit simulation request as a simulation request candidate to a first queuing queue; a second queue acquisition module for performing a first sorting process on each simulation request candidate in the first queuing queue based on a remaining simulation time of each simulation request candidate in the first queuing queue to obtain a second queuing queue; a target queue acquisition module that performs a second sorting process on the second queuing queue according to the magnitude of an acceleration parameter of each simulation request candidate in the second queuing queue to obtain a target queuing queue; a simulation processing module that performs simulation processing for each of the simulation request candidates by each of the simulation servers within a target processing period in accordance with the priority indicated by the target queuing queue.

9. A computer device comprising: a processor; and a memory storing at least one instruction, at least one program, code set or instruction set that is loaded and executed by the processor to implement the method for automatic parallel simulation of an integrated circuit according to any one of claims 1 to 7.

10. A computer-readable storage medium storing at least one instruction for implementing the method for automatic parallel simulation of an integrated circuit according to any one of claims 1 to 7 when the method is loaded and executed by a processor.

Citation Information

Patent Citations

  • Fault simulation system and allocating method for job

    JP1998134100A

  • Simulation execution method, execution device and recording medium

    JP1999031169A

  • Method for Unified High-Level Hardware Description Language Simulation Based on Parallel Computing Platforms

    US20130304450A1