Method, device and computer equipment for determining wiring parameters of power transmission network

Abstract

The present application relates to a method, device and computer equipment for determining wiring parameters of a power delivery network. The method includes: obtaining network structure information of the power delivery network, and generating initial wiring parameters of the network model of the power delivery network based on the network structure information; adjusting the first wiring parameters through a simulated annealing algorithm, and evaluating the first wiring parameters to obtain physical constraint evaluation information and current voltage wiring evaluation results; replacing the initial wiring parameters with the first wiring parameters, and returning to execute the above steps; until the physical constraint evaluation information meets the preset physical constraint conditions and the current voltage wiring evaluation results meet the voltage wiring conditions, the first wiring parameters are used as the target wiring parameters of the power delivery network. The use of this method can improve the efficiency of wiring design for power delivery networks.

Description

Technical Field

[0001] The present application relates to the technical field of wiring design of power transmission networks, and in particular to a method, device and computer equipment for determining wiring parameters of power transmission networks. Background Art

[0002] In chip design, the power delivery network (PDN) aims to provide ideal voltages for various components in the chip, so it plays an important role in signal integrity. A typical power delivery network consists of power pads, power stripes, vias, and power rails. The wiring design of the power delivery network can control the key parameters that affect the power delivery network, thereby optimizing the entire network. Therefore, how to unrestrictedly control the power delivery network is the current research focus.

[0003] The traditional wiring design method for power delivery networks is to manually design the wiring information of the power delivery network in the tool software, and then use machine learning methods to predict the predicted key parameters corresponding to the wiring information, so as to adjust the target wiring information. However, this method requires a lot of human resources and time resources, and manual wiring usually adopts an over-wiring strategy to meet the constraint of "the power supply voltage cannot drop too much", which occupies too many wiring metal layer resources, causing wiring congestion. Many wiring results cannot be used directly and have poor reliability, resulting in low efficiency in the wiring design of the power delivery network. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for determining wiring parameters of a power transmission network in order to address the above technical problems.

[0005] In a first aspect, the present application provides a method for determining wiring parameters of a power delivery network, comprising:

[0006] Acquire network structure information of a power transmission network, and generate a network model of the power transmission network and initial wiring parameters of the network model based on the network structure information;

[0007] In the network model, the initial wiring parameters are adjusted by a simulated annealing algorithm to obtain first wiring parameters, and the first wiring parameters are evaluated by a physical constraint evaluation strategy to obtain physical constraint evaluation information of the first wiring parameters;

[0008] Based on the voltage wiring evaluation strategy, the current voltage wiring evaluation result of the first wiring parameter is evaluated, and when the physical constraint evaluation information does not meet the physical constraint condition or the current voltage wiring evaluation result does not meet the voltage wiring condition, the first wiring parameter replaces the initial wiring parameter, returns to the execution in the network model, and adjusts the initial wiring parameter through a simulated annealing algorithm to obtain a first wiring parameter step;

[0009] Until the physical constraint evaluation information satisfies a preset physical constraint condition and the current voltage wiring evaluation result satisfies a voltage wiring condition, the first wiring parameter is used as a target wiring parameter of the power delivery network.

[0010] Optionally, generating a network model of the power delivery network and initial wiring parameters of the network model based on the network structure information includes:

[0011] Splitting the network structure information of the power transmission network into substructure information of each network structure, and acquiring the structural function of each network structure and the structural connection information of each network structure in the power transmission network database;

[0012] Based on the substructure information of each network structure, a substructure model of each network structure is constructed respectively through a modeling network, and each substructure model is subjected to model splicing processing through the structural connection information of each network structure to obtain a network structure model of the power transmission network;

[0013] Based on the structural functions of each of the network structures, generating functional parameters of each of the network structures in the network structure model, and adding the functional parameters of each of the network structures to each of the substructure models of the network structure model to obtain a network model;

[0014] Collecting historical design information of the power delivery network, and identifying wiring design information in the historical design information;

[0015] The wiring design information is added to the network model to obtain wiring structure information in the network model, and wiring parameters corresponding to the wiring structure information are identified to obtain initial wiring parameters of the network model.

[0016] Optionally, in the network model, adjusting the initial wiring parameters by a simulated annealing algorithm to obtain first wiring parameters includes:

[0017] The initial wiring parameters are adjusted by a preset parameter adjustment strategy to obtain first test wiring parameters, and based on the first test wiring parameters, a power transmission process of the network model to the chip is simulated to obtain simulation information;

[0018] Identify, by means of a voltage drop fast evaluator, a power supply voltage drop value graph from the power delivery network to the chip in the simulation information, and identify, by means of a fast router, a routing resource congestion value graph from the power delivery network to each metal layer of the chip;

[0019] Based on the power supply voltage drop value map and the wiring resource congestion value map, by presetting a first weight value of the power supply voltage drop value map and a second weight value of the presetting wiring resource congestion value map, calculating a simulated annealing score value corresponding to the test wiring parameter, and based on the simulated annealing score value, by a simulated annealing probability algorithm, adjusting the first test wiring parameter to obtain a second test wiring parameter;

[0020] The second test wiring parameters are used to replace the initial wiring parameters, and the step of adjusting the initial wiring parameters by a preset parameter adjustment strategy to obtain the first test wiring parameters is returned to execution, until a preset number of iterations is met, and the second test wiring parameters obtained in the last iteration are used as candidate first wiring parameters;

[0021] Based on the candidate first wiring parameter, identifying voltage drop information from the power delivery network to the chip through the network model;

[0022] In the case that the voltage drop information does not meet the preset voltage drop condition, the initial wiring parameter is replaced by the delivered candidate first wiring parameter, and the current iteration number and the preset iteration number are adjusted, and the process returns to the preset parameter adjustment strategy to adjust the initial wiring parameter to obtain the first test wiring parameter step, until the voltage drop information meets the preset voltage drop condition, and the candidate first wiring parameter corresponding to the voltage drop information that meets the preset voltage drop condition is used as the first wiring parameter.

[0023] Optionally, the evaluating the first wiring parameter by using a physical constraint evaluation strategy to obtain physical constraint evaluation information of the first wiring parameter includes:

[0024] Based on the first wiring parameters, in the network model, the wiring information of each wiring condition type from the power delivery network to each metal layer of the chip is identified, and the physical constraint evaluation strategy is split into sub-evaluation strategies of each wiring evaluation angle;

[0025] In the wiring database, query the wiring evaluation angle corresponding to each wiring condition type, and score the wiring information of each wiring condition type through the sub-evaluation strategy of the wiring evaluation angle corresponding to each wiring condition type to obtain the score value of each wiring condition type;

[0026] The score value of each type of wiring condition is used as the physical constraint evaluation information of the first wiring parameter.

[0027] Optionally, the evaluating a current voltage wiring evaluation result of the first wiring parameter based on a voltage wiring evaluation strategy includes:

[0028] Based on the first wiring parameter, the current voltage drop value from the power delivery network to the chip and the current wiring resource utilization rate are identified through the network model, and the voltage wiring evaluation strategy is split into a voltage drop evaluation strategy and a wiring resource evaluation strategy;

[0029] Based on the current voltage drop value, identifying the voltage drop evaluation result of the first wiring parameter through the voltage drop evaluation strategy, and based on the current wiring resource utilization, identifying the wiring resource evaluation result of the first wiring parameter through the wiring resource evaluation strategy;

[0030] The voltage drop evaluation result of the first wiring parameter and the wiring resource evaluation result of the first wiring parameter are used as the current voltage wiring evaluation result of the first wiring parameter.

[0031] Optionally, after evaluating the current voltage wiring evaluation result of the first wiring parameter based on the voltage wiring evaluation strategy, the method further includes:

[0032] Obtain physical constraints and voltage wiring conditions;

[0033] Based on the physical constraint condition, identifying a scoring threshold for each type of the wiring condition, and based on the voltage wiring condition, identifying a target voltage drop evaluation result and a target wiring resource evaluation result;

[0034] When there is a score value of each wiring condition type of the first wiring parameter that is lower than a score threshold of each wiring condition type, determining that the physical constraint evaluation information of the first wiring parameter does not satisfy the physical constraint condition;

[0035] When the voltage drop evaluation result of the first wiring parameter is different from the target voltage drop evaluation result, or the current voltage wiring evaluation result of the first wiring parameter is different from the target wiring resource evaluation result of the first wiring parameter, it is determined that the current voltage wiring evaluation result of the first wiring parameter does not meet the voltage wiring condition.

[0036] In a second aspect, the present application further provides a device for determining wiring parameters of a power transmission network, comprising:

[0037] An acquisition module, configured to acquire network structure information of a power transmission network, and generate a network model of the power transmission network and initial wiring parameters of the network model based on the network structure information;

[0038] A processing module, configured to adjust the initial wiring parameters in the network model by a simulated annealing algorithm to obtain first wiring parameters, and to evaluate the first wiring parameters by a physical constraint evaluation strategy to obtain physical constraint evaluation information of the first wiring parameters;

[0039] An adjustment module is used to evaluate the current voltage wiring evaluation result of the first wiring parameter based on the voltage wiring evaluation strategy, and replace the initial wiring parameter with the first wiring parameter when the physical constraint evaluation information does not meet the physical constraint condition or the current voltage wiring evaluation result does not meet the voltage wiring condition, and return to the execution in the network model, and adjust the initial wiring parameter through a simulated annealing algorithm to obtain a first wiring parameter step;

[0040] The determination module is configured to use the first wiring parameter as the target wiring parameter of the power delivery network until the physical constraint evaluation information satisfies a preset physical constraint condition and the current voltage wiring evaluation result satisfies a voltage wiring condition.

[0041] Optionally, the acquisition module is specifically used to:

[0042] Splitting the network structure information of the power transmission network into substructure information of each network structure, and acquiring the structural function of each network structure and the structural connection information of each network structure in the power transmission network database;

[0043] Based on the substructure information of each network structure, a substructure model of each network structure is constructed respectively through a modeling network, and each substructure model is subjected to model splicing processing through the structural connection information of each network structure to obtain a network structure model of the power transmission network;

[0044] Based on the structural functions of each of the network structures, generating functional parameters of each of the network structures in the network structure model, and adding the functional parameters of each of the network structures to each of the substructure models of the network structure model to obtain a network model;

[0045] Collecting historical design information of the power delivery network, and identifying wiring design information in the historical design information;

[0046] The wiring design information is added to the network model to obtain wiring structure information in the network model, and wiring parameters corresponding to the wiring structure information are identified to obtain initial wiring parameters of the network model.

[0047] Optionally, the processing module is specifically used to:

[0048] The initial wiring parameters are adjusted by a preset parameter adjustment strategy to obtain first test wiring parameters, and based on the first test wiring parameters, a power transmission process of the network model to the chip is simulated to obtain simulation information;

[0049] Identify, by means of a voltage drop fast evaluator, a power supply voltage drop value graph from the power delivery network to the chip in the simulation information, and identify, by means of a fast router, a routing resource congestion value graph from the power delivery network to each metal layer of the chip;

[0050] Based on the power supply voltage drop value map and the wiring resource congestion value map, by presetting a first weight value of the power supply voltage drop value map and a second weight value of the presetting wiring resource congestion value map, calculating a simulated annealing score value corresponding to the test wiring parameter, and based on the simulated annealing score value, by a simulated annealing probability algorithm, adjusting the first test wiring parameter to obtain a second test wiring parameter;

[0051] The second test wiring parameters are used to replace the initial wiring parameters, and the step of adjusting the initial wiring parameters by a preset parameter adjustment strategy to obtain the first test wiring parameters is returned to execution, until a preset number of iterations is met, and the second test wiring parameters obtained in the last iteration are used as candidate first wiring parameters;

[0052] Based on the candidate first wiring parameter, identifying voltage drop information from the power delivery network to the chip through the network model;

[0053] In the case that the voltage drop information does not meet the preset voltage drop condition, the initial wiring parameter is replaced by the delivered candidate first wiring parameter, and the current iteration number and the preset iteration number are adjusted, and the process returns to the preset parameter adjustment strategy to adjust the initial wiring parameter to obtain the first test wiring parameter step, until the voltage drop information meets the preset voltage drop condition, and the candidate first wiring parameter corresponding to the voltage drop information that meets the preset voltage drop condition is used as the first wiring parameter.

[0054] Optionally, the processing module is specifically used to:

[0055] Based on the first wiring parameters, in the network model, the wiring information of each wiring condition type from the power delivery network to each metal layer of the chip is identified, and the physical constraint evaluation strategy is split into sub-evaluation strategies of each wiring evaluation angle;

[0056] In the wiring database, query the wiring evaluation angle corresponding to each wiring condition type, and score the wiring information of each wiring condition type through the sub-evaluation strategy of the wiring evaluation angle corresponding to each wiring condition type to obtain the score value of each wiring condition type;

[0057] The score value of each type of wiring condition is used as the physical constraint evaluation information of the first wiring parameter.

[0058] Optionally, the adjustment module is specifically used to:

[0059] Based on the first wiring parameter, the current voltage drop value from the power delivery network to the chip and the current wiring resource utilization rate are identified through the network model, and the voltage wiring evaluation strategy is split into a voltage drop evaluation strategy and a wiring resource evaluation strategy;

[0060] Based on the current voltage drop value, identifying the voltage drop evaluation result of the first wiring parameter through the voltage drop evaluation strategy, and based on the current wiring resource utilization, identifying the wiring resource evaluation result of the first wiring parameter through the wiring resource evaluation strategy;

[0061] The voltage drop evaluation result of the first wiring parameter and the wiring resource evaluation result of the first wiring parameter are used as the current voltage wiring evaluation result of the first wiring parameter.

[0062] Optionally, the device further comprises:

[0063] A condition acquisition module, used to acquire physical constraint conditions and voltage wiring conditions;

[0064] An identification module, configured to identify a scoring threshold of each type of the wiring condition based on the physical constraint condition, and to identify a target voltage drop evaluation result and a target wiring resource evaluation result based on the voltage wiring condition;

[0065] A first judgment module, configured to determine that the physical constraint evaluation information of the first wiring parameter does not satisfy the physical constraint condition when the score value of each wiring condition type of the first wiring parameter is lower than the score threshold of each wiring condition type;

[0066] The second judgment module is used to determine that the current voltage wiring evaluation result of the first wiring parameter does not meet the voltage wiring condition when the voltage drop evaluation result of the first wiring parameter is different from the target voltage drop evaluation result, or the current voltage wiring evaluation result of the first wiring parameter is different from the target wiring resource evaluation result of the first wiring parameter.

[0067] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0068] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0069] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0070] The above-mentioned method, device and computer equipment for determining wiring parameters of the power delivery network obtain network structure information of the power delivery network, and generate a network model of the power delivery network and initial wiring parameters of the network model based on the network structure information; in the network model, the initial wiring parameters are adjusted by a simulated annealing algorithm to obtain first wiring parameters, and the first wiring parameters are evaluated by a physical constraint evaluation strategy to obtain physical constraint evaluation information of the first wiring parameters; based on a voltage wiring evaluation strategy, the current voltage wiring evaluation result of the first wiring parameter is evaluated, and when the physical constraint evaluation information does not meet the physical constraint condition or the current voltage wiring evaluation result does not meet the voltage wiring condition, the first wiring parameter replaces the initial wiring parameter, and returns to the step of adjusting the initial wiring parameter by a simulated annealing algorithm in the network model to obtain the first wiring parameter; until the physical constraint evaluation information meets the preset physical constraint condition and the current voltage wiring evaluation result meets the voltage wiring condition, the first wiring parameter is used as the target wiring parameter of the power delivery network. This solution aims to solve the problems of low efficiency and poor reliability in the existing power delivery network wiring technology. By establishing a network model and a simulated annealing algorithm, the initial wiring parameters of the power delivery network are adjusted to obtain the first wiring parameters, so that the chip power delivery network can be automatically planned and optimized to improve the reliability and efficiency of power supply to the internal units of the chip. Then, this solution comprehensively evaluates the functional integrity and wiring resource utilization of the power delivery network through physical constraint evaluation and voltage wiring evaluation, and can more accurately analyze the power delivery network status, thereby ensuring the wiring accuracy and avoiding the wiring congestion caused by excessive wiring, so as to ensure that the power delivery network maintains the best state in actual work. Finally, the intelligent wiring method of this solution avoids the problems of excessive wiring of manual wiring and excessive consumption of human resources and time resources, thereby comprehensively improving the wiring design efficiency of the power delivery network. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0072] Figure 1 A schematic flow chart of a method for determining wiring parameters of a power delivery network in one embodiment;

[0073] Figure 2A schematic diagram of an example flow chart of determining wiring parameters of a power delivery network in one embodiment;

[0074] Figure 3 A structural block diagram of a device for determining wiring parameters of a power transmission network in one embodiment;

[0075] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0076] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0077] The method for determining the wiring parameters of the power delivery network provided in the embodiment of the present application can be applied to the application environment of the wiring design of the power delivery network. Among them, the method can be applied to the terminal, can also be applied to the server, and can also be applied to the system including the terminal and the server, and is realized through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, etc. Among them, the terminal adjusts the initial wiring parameters of the power delivery network by establishing a network model and a simulated annealing algorithm to obtain the first wiring parameters in view of the low efficiency and poor reliability existing in the existing power delivery network wiring technology, so as to automatically plan and optimize the chip power delivery network and improve the reliability and efficiency of power supply to the internal units of the chip. Then, this scheme comprehensively evaluates the functional integrity and wiring resource utilization of the power delivery network from the perspective of physical constraint evaluation and voltage wiring evaluation, and can more accurately analyze the power delivery network status, thereby ensuring the wiring accuracy while avoiding the wiring congestion caused by excessive wiring, so as to ensure that the power delivery network maintains the best state in actual work. Finally, the intelligent wiring method of this scheme avoids the problems of excessive wiring of manual wiring and excessive consumption of human resources and time resources, thereby comprehensively improving the wiring design efficiency of the power delivery network.

[0078] In an exemplary embodiment, Figure 1 As shown, a method for determining wiring parameters of a power transmission network is provided, and the method is applied to a terminal as an example for explanation, including the following steps S101 to S104. Among them:

[0079] Step S101, obtaining network structure information of a power transmission network, and generating a network model of the power transmission network and initial wiring parameters of the network model based on the network structure information.

[0080] In this embodiment, the terminal obtains the network structure information of the power transmission network in response to the information upload operation of the staff, wherein the network structure information includes sub-network structure information of multiple network structures. The network structure includes power pads, power stripes, vias, and power rails, etc. Among them, each sub-network structure information is the three-dimensional scanning structure data of each network structure, and then the terminal generates a network model of the power transmission network and the initial wiring parameters of the network model based on the network structure information. Among them, the network model is a simulation model built based on the power transmission network. In addition to the power transmission network, the simulation model also includes a chip, wherein the wiring parameters are the transmission line wiring for the power transmission network in the principle model to transmit current to each metal layer of the chip. The specific construction process will be described in detail later. Among them, each wiring parameter includes the parameters corresponding to the wiring design information of each transmission line wiring.

[0081] Step S102, in the network model, adjusting the initial wiring parameters by a simulated annealing algorithm to obtain first wiring parameters, and evaluating the first wiring parameters by a physical constraint evaluation strategy to obtain physical constraint evaluation information of the first wiring parameters.

[0082] In this embodiment, the terminal adjusts the initial wiring parameters in the network model through the simulated annealing algorithm to obtain the first wiring parameters, and evaluates the first wiring parameters through the physical constraint evaluation strategy to obtain the physical constraint evaluation information of the first wiring parameters. The simulated annealing algorithm is an optimization algorithm that optimizes and adjusts the number of layers of wiring in the power transmission network, the direction, width, spacing (sparseness) of the power strips in each layer, and the position and number of through holes through the simulated annealing probability criterion. The optimization algorithm corresponds to an optimization iteration process, and the specific optimization process will be described in detail later. The physical constraint evaluation strategy is a detection strategy for checking the rules of the physical constraints of the power transmission network. The strategy is preset in the terminal, and the physical constraint evaluation information includes evaluation information for evaluating the overlapping information, intersection information, and through hole information of the wiring. The specific evaluation process will be described in detail later.

[0083] Step S103, based on the voltage wiring evaluation strategy, evaluate the current voltage wiring evaluation result of the first wiring parameter, and when the physical constraint evaluation information does not meet the physical constraint conditions, or the current voltage wiring evaluation result does not meet the voltage wiring conditions, replace the initial wiring parameters with the first wiring parameters, return to the execution in the network model, adjust the initial wiring parameters through the simulated annealing algorithm, and obtain the first wiring parameter step.

[0084] In this embodiment, the terminal evaluates the current voltage wiring evaluation result of the first wiring parameter based on the voltage wiring evaluation strategy, and replaces the initial wiring parameter with the first wiring parameter when the physical constraint evaluation information does not meet the physical constraint condition or the current voltage wiring evaluation result does not meet the voltage wiring condition, and returns to the execution in the network model, and adjusts the initial wiring parameter through the simulated annealing algorithm to obtain the first wiring parameter step. Among them, the voltage wiring evaluation strategy includes a voltage drop evaluation strategy and a wiring resource evaluation strategy. Among them, the voltage drop evaluation strategy is an evaluation strategy for evaluating the voltage drop value transmitted from the power delivery network to the chip; the wiring resource evaluation strategy is an evaluation strategy for evaluating the wiring information of each metal layer transmitted from the power delivery network to the chip. The specific evaluation process will be described in detail later.

[0085] Step S104 , until the physical constraint evaluation information satisfies the preset physical constraint condition and the current voltage wiring evaluation result satisfies the voltage wiring condition, the first wiring parameter is used as the target wiring parameter of the power delivery network.

[0086] In this embodiment, the terminal uses the first wiring parameter as the target wiring parameter of the power delivery network until the physical constraint evaluation information meets the preset physical constraint conditions and the current voltage wiring evaluation result meets the voltage wiring condition. The physical constraint conditions are physical performance conditions such as no overlap, no intersection, and no through holes being too dense. The voltage wiring condition is that the voltage drop value meets the requirements (within a threshold) and the utilization rate of wiring resources is high. The specific process of determining whether the physical constraint evaluation information meets the preset physical constraint conditions and whether the current voltage wiring evaluation result meets the voltage wiring condition will be described in detail later.

[0087] Based on the above scheme, in order to solve the problems of low efficiency and poor reliability in the existing power delivery network wiring technology, the initial wiring parameters of the power delivery network are adjusted by establishing a network model and a simulated annealing algorithm to obtain the first wiring parameters, so that the chip power delivery network can be automatically planned and optimized to improve the reliability and efficiency of power supply to the internal units of the chip. Then, this scheme comprehensively evaluates the functional integrity and wiring resource utilization of the power delivery network by means of physical constraint evaluation and voltage wiring evaluation, so as to more accurately analyze the power delivery network status, thereby ensuring the wiring accuracy and avoiding the wiring congestion caused by excessive wiring, so as to ensure that the power delivery network maintains the best state in actual work. Finally, the intelligent wiring method of this scheme avoids the problems of excessive wiring of manual wiring and excessive consumption of human resources and time resources, thereby comprehensively improving the wiring design efficiency of the power delivery network.

[0088] Optionally, based on the network structure information, a network model of the power transmission network and initial wiring parameters of the network model are generated, including: splitting the network structure information of the power transmission network into substructure information of each network structure, and obtaining the structural function of each network structure and the structural connection information of each network structure in the power transmission network database; based on the substructure information of each network structure, respectively constructing a substructure model of each network structure by modeling the network, and performing model splicing processing on each substructure model through the structural connection information of each network structure to obtain the network structure model of the power transmission network; based on the structural function of each network structure, generating functional parameters of each network structure in the network structure model, and adding the functional parameters of each network structure to each substructure model of the network structure model to obtain a network model; collecting historical design information of the power transmission network, and identifying wiring design information in the historical design information; adding the wiring design information to the network model to obtain wiring structure information in the network model, and identifying wiring parameters corresponding to the wiring structure information to obtain initial wiring parameters of the network model.

[0089] In this embodiment, the terminal splits the network structure information of the power transmission network into substructure information of each network structure, and obtains the structural function of each network structure and the structural connection information of each network structure in the power transmission network database. The structural function information of each network structure is the operating function of each network structure in the power transmission network.

[0090] Based on the substructure information of each network structure, the terminal constructs a substructure model of each network structure through a modeling network, and performs model splicing processing on each substructure model through the structural connection information of each network structure to obtain a network structure model of the power transmission network. The modeling network can be, but is not limited to, a modeling network based on a finite element modeling program.

[0091] The terminal generates the functional parameters of each network structure in the network structure model based on the structural functions of each network structure, and adds the functional parameters of each network structure to each substructure model of the network structure model to obtain a network model. The functional parameters of each network structure are functional parameters used to simulate the operation process of each network structure.

[0092] The terminal collects the historical design information of the power transmission network and identifies the wiring design information in the historical design information. The historical design information is the transmission information of the power transmission network by the staff. The terminal uses the initial wiring parameters corresponding to the wiring design information of the historical design information as the initial parameters for optimization, thereby reducing the optimization time, avoiding the disorder and irrationality of the randomly generated initial wiring parameters, and avoiding the inefficiency of the optimization results that require a long time to optimize.

[0093] The terminal adds the wiring design information to the network model, obtains the wiring structure information in the network model, identifies the wiring parameters corresponding to the wiring structure information, and obtains the initial wiring parameters of the network model.

[0094] Based on the above scheme, after building the structural model, the network model is obtained by adding functions, which improves the simulation effect of building the network model. Finally, the wiring design information in the historical design information generates the initial wiring parameters of the network model, which improves the rationality and orderliness of the initial wiring parameters, thereby improving the optimization efficiency of the initial wiring parameters.

[0095] Optionally, in the network model, the initial wiring parameters are adjusted through a simulated annealing algorithm to obtain first wiring parameters, including: adjusting the initial wiring parameters through a preset parameter adjustment strategy to obtain first test wiring parameters, and based on the first test wiring parameters, simulating the power delivery process of the network model to the chip to obtain simulation information; identifying the power supply voltage drop value graph from the power supply network to the chip in the simulation information through a voltage drop fast evaluator, and identifying the wiring resource congestion value graph from the power supply network to each metal layer of the chip through a fast router; based on the power supply voltage drop value graph and the wiring resource congestion value graph, calculating the simulated annealing score value corresponding to the test wiring parameters through a preset first weight value of the power supply voltage drop value graph and a preset second weight value of the wiring resource congestion value graph, and adjusting the first test wiring parameters through a simulated annealing probability algorithm based on the simulated annealing score value to obtain a second test wiring parameter. Test wiring parameters; replace the initial wiring parameters with the second test wiring parameters, and return to execute the preset parameter adjustment strategy to adjust the initial wiring parameters to obtain the first test wiring parameter step, until the preset number of iterations is met, the second test wiring parameters obtained in the last iteration are used as candidate first wiring parameters; based on the candidate first wiring parameters, the voltage drop information from the power supply transmission network to the chip is identified through the network model; when the voltage drop information does not meet the preset voltage drop condition, the initial wiring parameters are replaced by the transmitted candidate first wiring parameters, and the current number of iterations and the preset number of iterations are adjusted, and return to execute the preset parameter adjustment strategy to adjust the initial wiring parameters to obtain the first test wiring parameter step, until the voltage drop information meets the preset voltage drop condition, the candidate first wiring parameters corresponding to the voltage drop information that meets the preset voltage drop condition are used as the first wiring parameters.

[0096] In this embodiment, the terminal adjusts the initial wiring parameters through a preset parameter adjustment strategy to obtain the first test wiring parameters, and based on the first test wiring parameters, simulates the power transmission process of the network model to the chip to obtain simulation information. The simulation information includes voltage change information transmitted to the chip by the power transmission network at different times, simulated power transmission conditions of each transmission line (that is, part of the transmission line is used to transmit power, while part of the transmission line will not be used), etc.

[0097] The terminal uses a voltage drop fast evaluator (a voltage drop evaluator provided in the open source electronic design automation tool "iEDA", https: / / github.com / OSCC-Project / iEDA) to identify the power supply voltage drop value graph from the power delivery network to the chip in the simulation information, and uses a fast router (a router provided in the open source electronic design automation tool "iEDA", https: / / github.com / OSCC-Project / iEDA) to identify the wiring resource congestion value graph from the power delivery network to each metal layer of the chip. Among them, the power supply voltage drop value graph is the voltage drop value corresponding to different delivery positions when the power is delivered from the power delivery network to the chip. The wiring resource congestion value graph is the wiring resource congestion value corresponding to different delivery positions when the power is delivered from the power delivery network to the chip.

[0098] Then, based on the power supply voltage drop value map and the wiring resource congestion value map, the terminal calculates the simulated annealing score value corresponding to the test wiring parameter by presetting the first weight value of the power supply voltage drop value map and the second weight value of the wiring resource congestion value map. The calculation process of the simulated annealing score value is to calculate the average value of the voltage drop value between the chips from the power supply network multiplied by the first weight value, and add the average value of the wiring resource congestion value between the chips from the power supply network multiplied by the second weight value, and then sum them up to obtain the value.

[0099] Then, the terminal adjusts the first test wiring parameters based on the simulated annealing score value and obtains the second test wiring parameters by using a simulated annealing probability algorithm. The simulated annealing probability algorithm is:

[0100]

[0101] Where T is the preset number of iterations, k is a coefficient, Indicates the simulated annealing score value calculated from the first test wiring parameters obtained last time. Indicates the simulated annealing score value calculated based on the first test wiring parameters obtained this time.

[0102] The terminal replaces the initial wiring parameters with the second test wiring parameters, and returns to execute the step of adjusting the initial wiring parameters through the preset parameter adjustment strategy to obtain the first test wiring parameter step, until the preset number of iterations is met, and the second test wiring parameters obtained in the last iteration are used as candidate first wiring parameters.

[0103] The terminal identifies the voltage drop information from the power supply network to the chip through the network model based on the candidate first wiring parameters. Then, if the voltage drop information does not meet the preset voltage drop condition, the terminal replaces the initial wiring parameters with the transmitted candidate first wiring parameters, adjusts the current number of iterations and the preset number of iterations, returns to execute the preset parameter adjustment strategy, adjusts the initial wiring parameters, and obtains the first test wiring parameter step, until the voltage drop information meets the preset voltage drop condition, the candidate first wiring parameters corresponding to the voltage drop information that meets the preset voltage drop condition are used as the first wiring parameters. The preset voltage drop condition is whether the voltage drop value is within a threshold range.

[0104] Based on the above scheme, by calculating the simulated annealing score value, the initial wiring information is adjusted to ensure that the voltage drop meets the requirements (within a threshold), and the power supply strips cannot overlap or intersect, and the through holes cannot be too dense, etc., which improves the wiring information obtained after optimization. The voltage drop is lower and the wiring distribution is more reasonable, thereby improving the wiring utilization rate.

[0105] Optionally, the first wiring parameter is evaluated and processed through a physical constraint evaluation strategy to obtain physical constraint evaluation information of the first wiring parameter, including: based on the first wiring parameter, in the network model, identifying the wiring information of each wiring condition type from the power delivery network to each metal layer of the chip, and splitting the physical constraint evaluation strategy into sub-evaluation strategies for each wiring evaluation angle; in the wiring database, querying the wiring evaluation angle corresponding to each wiring condition type, and scoring the wiring information of each wiring condition type through the sub-evaluation strategy of the wiring evaluation angle corresponding to each wiring condition type to obtain a scoring value for each wiring condition type; using the scoring value of each wiring condition type as the physical constraint evaluation information of the first wiring parameter.

[0106] In this embodiment, based on the first wiring parameter, the terminal identifies the wiring information of each wiring condition type from the power delivery network to each metal layer of the chip in the network model, and splits the physical constraint evaluation strategy into sub-evaluation strategies for each wiring evaluation angle. The wiring evaluation angles include, but are not limited to, wiring overlap evaluation angles, wiring intersection evaluation angles, wiring through-hole evaluation angles, etc. The wiring condition types include, but are not limited to, overlapping wiring types, intersection wiring types, through-hole wiring types, etc.

[0107] Then, the terminal queries the wiring evaluation angle corresponding to each wiring condition type in the wiring database, and scores the wiring information of each wiring condition type through the sub-evaluation strategy of the wiring evaluation angle corresponding to each wiring condition type to obtain the score value of each wiring condition type. Among them, the sub-evaluation strategy of each wiring evaluation angle includes the score value corresponding to the wiring degree range of each wiring information, and each wiring information includes the wiring degree value of each wiring evaluation angle. Finally, the terminal uses the score value of each wiring condition type as the physical constraint evaluation information of the first wiring parameter.

[0108] Based on the above scheme, by evaluating and processing different wiring condition types separately, the score value of each wiring adjustment type is obtained, thereby improving the comprehensiveness of the analysis of the wiring condition type and the evaluation accuracy of the physical constraint evaluation information.

[0109] Optionally, based on the voltage routing evaluation strategy, the current voltage routing evaluation result of the first routing parameter is evaluated, including: based on the first routing parameter, through the network model, identifying the current voltage drop value of the power delivery network to the chip and the current routing resource utilization, and splitting the voltage routing evaluation strategy into a voltage drop evaluation strategy and a routing resource evaluation strategy; based on the current voltage drop value, identifying the voltage drop evaluation result of the first routing parameter through the voltage drop evaluation strategy, and based on the current routing resource utilization, identifying the routing resource evaluation result of the first routing parameter through the routing resource evaluation strategy; using the voltage drop evaluation result of the first routing parameter and the routing resource evaluation result of the first routing parameter as the current voltage routing evaluation result of the first routing parameter.

[0110] In this embodiment, the terminal identifies the current voltage drop value of the power supply network to the chip and the current wiring resource utilization rate through the network model based on the first wiring parameter, and splits the voltage wiring evaluation strategy into a voltage drop evaluation strategy and a wiring resource evaluation strategy. Based on the current voltage drop value, the voltage drop evaluation result of the first wiring parameter is identified through the voltage drop evaluation strategy. The specific identification process is that the voltage drop evaluation strategy includes a voltage drop value range corresponding to each voltage drop evaluation result. For example, the voltage drop evaluation result corresponding to the A range is that the voltage drop is reasonable, and the voltage drop evaluation result corresponding to the B range is that the voltage drop is unreasonable. The terminal determines the voltage drop evaluation result corresponding to the first wiring parameter by identifying the voltage drop value range described by the current voltage drop value corresponding to the first wiring parameter.

[0111] The terminal identifies the wiring resource evaluation result of the first wiring parameter based on the current wiring resource utilization and the wiring resource evaluation strategy. The wiring resource evaluation strategy includes wiring resource evaluation results corresponding to different wiring resource utilization ranges. Then, the terminal identifies the wiring resource evaluation result of the first wiring parameter by identifying the wiring resource utilization range to which the current wiring resource utilization belongs. The wiring resource evaluation results include, but are not limited to, four results: unreasonable wiring, relatively unreasonable wiring, relatively reasonable wiring, and reasonable wiring.

[0112] Finally, the terminal uses the voltage drop evaluation result of the first wiring parameter and the wiring resource evaluation result of the first wiring parameter as the current voltage wiring evaluation result of the first wiring parameter.

[0113] Based on the above scheme, the voltage drop evaluation result of the first wiring parameter and the wiring resource evaluation result of the first wiring parameter are identified through range query, so as to obtain the current voltage wiring evaluation result of the first wiring parameter, thereby improving the recognition efficiency and accuracy of the current voltage wiring evaluation result of the first wiring parameter.

[0114] Optionally, after evaluating the current voltage wiring evaluation result of the first wiring parameter based on the voltage wiring evaluation strategy, it also includes: obtaining physical constraints and voltage wiring conditions; identifying the scoring threshold of each wiring condition type based on the physical constraints, and identifying the target voltage drop evaluation result and the target wiring resource evaluation result based on the voltage wiring conditions; when the score value of each wiring condition type of the first wiring parameter is lower than the scoring threshold of each wiring condition type, determining that the physical constraint evaluation information of the first wiring parameter does not meet the physical constraints; when the voltage drop evaluation result of the first wiring parameter is different from the target voltage drop evaluation result, or the current voltage wiring evaluation result of the first wiring parameter is different from the target wiring resource evaluation result of the first wiring parameter, determining that the current voltage wiring evaluation result of the first wiring parameter does not meet the voltage wiring conditions.

[0115] In this embodiment, the terminal obtains physical constraints and voltage wiring conditions. Then, the terminal identifies the scoring threshold of each wiring condition type based on the physical constraints, and identifies the target voltage drop evaluation result and the target wiring resource evaluation result based on the voltage wiring condition. Among them, the target voltage drop evaluation result is that the voltage drop is reasonable. The target wiring resource evaluation result includes that the wiring is relatively reasonable and the wiring is reasonable.

[0116] When the score value of each wiring condition type of the first wiring parameter is lower than the score threshold of each wiring condition type, it is determined that the physical constraint evaluation information of the first wiring parameter does not meet the physical constraint condition. When the voltage drop evaluation result of the first wiring parameter is different from the target voltage drop evaluation result, or the current voltage wiring evaluation result of the first wiring parameter is different from the target wiring resource evaluation result of the first wiring parameter, it is determined that the current voltage wiring evaluation result of the first wiring parameter does not meet the voltage wiring condition.

[0117] Based on the above scheme, by limiting the scoring threshold of the physical constraint conditions, the target voltage drop evaluation results of the voltage wiring conditions, and the target wiring resource evaluation results, it is possible to judge whether the physical constraint conditions or the voltage wiring conditions are met, thereby improving the accuracy and efficiency of the judgment.

[0118] The present application also provides an example of determining wiring parameters of a power delivery network, such as Figure 2 As shown, the specific processing process includes the following steps:

[0119] Step S201, obtaining network structure information of a power transmission network.

[0120] Step S202 : splitting the network structure information of the power transmission network into substructure information of each network structure, and acquiring the structure function of each network structure and the structure connection information of each network structure in the power transmission network database.

[0121] Step S203, based on the substructure information of each network structure, by modeling the network, respectively construct the substructure model of each network structure, and by using the structural connection information of each network structure, perform model splicing processing on each substructure model to obtain the network structure model of the power transmission network.

[0122] Step S204, based on the structural functions of each network structure, generating functional parameters of each network structure in the network structure model, and adding the functional parameters of each network structure to each substructure model of the network structure model to obtain a network model.

[0123] Step S205 , collecting historical design information of the power delivery network, and identifying wiring design information in the historical design information.

[0124] Step S206, adding the wiring design information to the network model, obtaining the wiring structure information in the network model, and identifying the wiring parameters corresponding to the wiring structure information to obtain the initial wiring parameters of the network model.

[0125] Step S207, adjusting the initial wiring parameters through a preset parameter adjustment strategy to obtain first test wiring parameters, and simulating the power transmission process of the network model to the chip based on the first test wiring parameters to obtain simulation information.

[0126] Step S208, identifying the power supply voltage drop value graph from the power delivery network to the chip in the simulation information through the voltage drop fast evaluator, and identifying the wiring resource congestion value graph from the power delivery network to each metal layer of the chip through the fast router.

[0127] Step S209, based on the power supply voltage drop value map and the wiring resource congestion value map, calculate the simulated annealing score value corresponding to the test wiring parameters by presetting the first weight value of the power supply voltage drop value map and the second weight value of the preset wiring resource congestion value map, and based on the simulated annealing score value, adjust the first test wiring parameters through the simulated annealing probability algorithm to obtain the second test wiring parameters.

[0128] Step S210, replace the initial wiring parameters with the second test wiring parameters, and return to execute the preset parameter adjustment strategy to adjust the initial wiring parameters to obtain the first test wiring parameters step, until the preset number of iterations is met, and the second test wiring parameters obtained in the last iteration are used as candidate first wiring parameters.

[0129] Step S211 , based on the candidate first wiring parameters, identifying voltage drop information from the power delivery network to the chip through a network model.

[0130] Step S212, when the voltage drop information does not meet the preset voltage drop condition, the transmitted candidate first wiring parameter replaces the initial wiring parameter, and adjusts the current number of iterations and the preset number of iterations, returns to execute the preset parameter adjustment strategy, adjusts the initial wiring parameter, and obtains the first test wiring parameter step, until the voltage drop information meets the preset voltage drop condition, the candidate first wiring parameter corresponding to the voltage drop information that meets the preset voltage drop condition is used as the first wiring parameter.

[0131] Step S213, based on the first wiring parameter, in the network model, identifying the wiring information of each wiring condition type from the power delivery network to each metal layer of the chip, and splitting the physical constraint evaluation strategy into sub-evaluation strategies for each wiring evaluation angle.

[0132] Step S214, in the wiring database, query the wiring evaluation angle corresponding to each wiring condition type, and score the wiring information of each wiring condition type through the sub-evaluation strategy of the wiring evaluation angle corresponding to each wiring condition type to obtain the score value of each wiring condition type.

[0133] Step S215 : Using the score value of each routing condition type as physical constraint evaluation information of the first routing parameter.

[0134] Step S216, based on the first wiring parameter, through the network model, identify the current voltage drop value from the power delivery network to the chip and the current wiring resource utilization, and split the voltage wiring evaluation strategy into a voltage drop evaluation strategy and a wiring resource evaluation strategy.

[0135] Step S217, based on the current voltage drop value, using the voltage drop evaluation strategy, identifying the voltage drop evaluation result of the first wiring parameter, and based on the current wiring resource utilization, using the wiring resource evaluation strategy, identifying the wiring resource evaluation result of the first wiring parameter.

[0136] Step S218: Using the voltage drop evaluation result of the first wiring parameter and the wiring resource evaluation result of the first wiring parameter as the current voltage wiring evaluation result of the first wiring parameter.

[0137] Step S219, obtaining physical constraint conditions and voltage wiring conditions.

[0138] Step S220 , identifying the scoring threshold of each type of wiring condition based on the physical constraint condition, and identifying the target voltage drop evaluation result and the target wiring resource evaluation result based on the voltage wiring condition.

[0139] Step S221 : when there is a score value of each wiring condition type of the first wiring parameter that is lower than a score threshold of each wiring condition type, determining that the physical constraint evaluation information of the first wiring parameter does not satisfy the physical constraint condition.

[0140] Step S222, when the voltage drop evaluation result of the first wiring parameter is different from the target voltage drop evaluation result, or the current voltage wiring evaluation result of the first wiring parameter is different from the target wiring resource evaluation result of the first wiring parameter, it is determined that the current voltage wiring evaluation result of the first wiring parameter does not meet the voltage wiring condition.

[0141] Step S223, when the physical constraint evaluation information does not meet the physical constraint conditions, or the current voltage wiring evaluation result does not meet the voltage wiring conditions, the first wiring parameters are replaced by the initial wiring parameters, and the execution is returned to the network model. The initial wiring parameters are adjusted through the simulated annealing algorithm to obtain the first wiring parameter step.

[0142] Step S224 , until the physical constraint evaluation information satisfies the preset physical constraint condition and the current voltage wiring evaluation result satisfies the voltage wiring condition, the first wiring parameter is used as the target wiring parameter of the power delivery network.

[0143] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0144] Based on the same inventive concept, the embodiment of the present application also provides a device for determining wiring parameters of a power transmission network for implementing the method for determining wiring parameters of a power transmission network involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more devices for determining wiring parameters of a power transmission network provided below can refer to the limitations of the method for determining wiring parameters of a power transmission network above, and will not be repeated here.

[0145] In an exemplary embodiment, Figure 3 As shown, a device for determining wiring parameters of a power delivery network is provided, comprising: an acquisition module 310, a processing module 320, an adjustment module 330 and a determination module 340, wherein:

[0146] An acquisition module 310 is used to acquire network structure information of a power transmission network, and based on the network structure information, generate a network model of the power transmission network and initial wiring parameters of the network model;

[0147] A processing module 320 is used to adjust the initial wiring parameters in the network model by a simulated annealing algorithm to obtain first wiring parameters, and to evaluate the first wiring parameters by a physical constraint evaluation strategy to obtain physical constraint evaluation information of the first wiring parameters;

[0148] An adjustment module 330 is used to evaluate the current voltage wiring evaluation result of the first wiring parameter based on the voltage wiring evaluation strategy, and replace the initial wiring parameter with the first wiring parameter when the physical constraint evaluation information does not meet the physical constraint condition or the current voltage wiring evaluation result does not meet the voltage wiring condition, and return to the execution in the network model, and adjust the initial wiring parameter through a simulated annealing algorithm to obtain a first wiring parameter step;

[0149] The determination module 340 is configured to use the first wiring parameter as the target wiring parameter of the power delivery network until the physical constraint evaluation information satisfies a preset physical constraint condition and the current voltage wiring evaluation result satisfies a voltage wiring condition.

[0150] Optionally, the acquisition module 310 is specifically configured to:

[0151] Splitting the network structure information of the power transmission network into substructure information of each network structure, and acquiring the structural function of each network structure and the structural connection information of each network structure in the power transmission network database;

[0152] Based on the substructure information of each network structure, a substructure model of each network structure is constructed respectively through a modeling network, and each substructure model is subjected to model splicing processing through the structural connection information of each network structure to obtain a network structure model of the power transmission network;

[0153] Based on the structural functions of each of the network structures, generating functional parameters of each of the network structures in the network structure model, and adding the functional parameters of each of the network structures to each of the substructure models of the network structure model to obtain a network model;

[0154] Collecting historical design information of the power delivery network, and identifying wiring design information in the historical design information;

[0155] The wiring design information is added to the network model to obtain wiring structure information in the network model, and wiring parameters corresponding to the wiring structure information are identified to obtain initial wiring parameters of the network model.

[0156] Optionally, the processing module 320 is specifically configured to:

[0157] The initial wiring parameters are adjusted by a preset parameter adjustment strategy to obtain first test wiring parameters, and based on the first test wiring parameters, a power transmission process of the network model to the chip is simulated to obtain simulation information;

[0158] Identify, by means of a voltage drop fast evaluator, a power supply voltage drop value graph from the power delivery network to the chip in the simulation information, and identify, by means of a fast router, a routing resource congestion value graph from the power delivery network to each metal layer of the chip;

[0159] Based on the power supply voltage drop value map and the wiring resource congestion value map, by presetting a first weight value of the power supply voltage drop value map and a second weight value of the presetting wiring resource congestion value map, calculating a simulated annealing score value corresponding to the test wiring parameter, and based on the simulated annealing score value, by a simulated annealing probability algorithm, adjusting the first test wiring parameter to obtain a second test wiring parameter;

[0160] The second test wiring parameters are used to replace the initial wiring parameters, and the step of adjusting the initial wiring parameters by a preset parameter adjustment strategy to obtain the first test wiring parameters is returned to execution, until a preset number of iterations is met, and the second test wiring parameters obtained in the last iteration are used as candidate first wiring parameters;

[0161] Based on the candidate first wiring parameter, identifying voltage drop information from the power delivery network to the chip through the network model;

[0162] In the case that the voltage drop information does not meet the preset voltage drop condition, the initial wiring parameter is replaced by the delivered candidate first wiring parameter, and the current iteration number and the preset iteration number are adjusted, and the process returns to the preset parameter adjustment strategy to adjust the initial wiring parameter to obtain the first test wiring parameter step, until the voltage drop information meets the preset voltage drop condition, and the candidate first wiring parameter corresponding to the voltage drop information that meets the preset voltage drop condition is used as the first wiring parameter.

[0163] Optionally, the processing module 320 is specifically configured to:

[0164] Based on the first wiring parameters, in the network model, the wiring information of each wiring condition type from the power delivery network to each metal layer of the chip is identified, and the physical constraint evaluation strategy is split into sub-evaluation strategies of each wiring evaluation angle;

[0165] In the wiring database, query the wiring evaluation angle corresponding to each wiring condition type, and score the wiring information of each wiring condition type through the sub-evaluation strategy of the wiring evaluation angle corresponding to each wiring condition type to obtain the score value of each wiring condition type;

[0166] The score value of each type of wiring condition is used as the physical constraint evaluation information of the first wiring parameter.

[0167] Optionally, the adjustment module 330 is specifically configured to:

[0168] Based on the first wiring parameter, the current voltage drop value from the power delivery network to the chip and the current wiring resource utilization rate are identified through the network model, and the voltage wiring evaluation strategy is split into a voltage drop evaluation strategy and a wiring resource evaluation strategy;

[0169] Based on the current voltage drop value, identifying the voltage drop evaluation result of the first wiring parameter through the voltage drop evaluation strategy, and based on the current wiring resource utilization, identifying the wiring resource evaluation result of the first wiring parameter through the wiring resource evaluation strategy;

[0170] The voltage drop evaluation result of the first wiring parameter and the wiring resource evaluation result of the first wiring parameter are used as the current voltage wiring evaluation result of the first wiring parameter.

[0171] Optionally, the device further comprises:

[0172] A condition acquisition module, used to acquire physical constraint conditions and voltage wiring conditions;

[0173] An identification module, configured to identify a scoring threshold of each type of the wiring condition based on the physical constraint condition, and to identify a target voltage drop evaluation result and a target wiring resource evaluation result based on the voltage wiring condition;

[0174] A first judgment module, configured to determine that the physical constraint evaluation information of the first wiring parameter does not satisfy the physical constraint condition when the score value of each wiring condition type of the first wiring parameter is lower than the score threshold of each wiring condition type;

[0175] The second judgment module is used to determine that the current voltage wiring evaluation result of the first wiring parameter does not meet the voltage wiring condition when the voltage drop evaluation result of the first wiring parameter is different from the target voltage drop evaluation result, or the current voltage wiring evaluation result of the first wiring parameter is different from the target wiring resource evaluation result of the first wiring parameter.

[0176] Each module in the above-mentioned device for determining wiring parameters of a power transmission network can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0177] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for determining wiring parameters of a power transmission network is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0178] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0179] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0180] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0181] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0182] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0183] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0184] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0185] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining wiring parameters of a power transmission network, characterized in that: The method comprises: Acquire network structure information of a power transmission network, and generate a network model of the power transmission network and initial wiring parameters of the network model based on the network structure information; The initial wiring parameters are adjusted by a preset parameter adjustment strategy to obtain first test wiring parameters, and based on the first test wiring parameters, a power transmission process of the network model to the chip is simulated to obtain simulation information; Identify, by means of a voltage drop fast evaluator, a power supply voltage drop value graph from the power delivery network to the chip in the simulation information, and identify, by means of a fast router, a routing resource congestion value graph from the power delivery network to each metal layer of the chip; Based on the power supply voltage drop value map and the wiring resource congestion value map, by presetting a first weight value of the power supply voltage drop value map and a second weight value of the presetting wiring resource congestion value map, calculating a simulated annealing score value corresponding to the test wiring parameter, and based on the simulated annealing score value, by a simulated annealing probability algorithm, adjusting the first test wiring parameter to obtain a second test wiring parameter; The second test wiring parameters are used to replace the initial wiring parameters, and the step of adjusting the initial wiring parameters by a preset parameter adjustment strategy to obtain the first test wiring parameters is returned to execution, until a preset number of iterations is met, and the second test wiring parameters obtained in the last iteration are used as candidate first wiring parameters; Based on the candidate first wiring parameter, identifying voltage drop information from the power delivery network to the chip through the network model; In the case where the voltage drop information does not meet the preset voltage drop condition, the initial wiring parameter is replaced by the delivered candidate first wiring parameter, and the current iteration number and the preset iteration number are adjusted, and the step of adjusting the initial wiring parameter by the preset parameter adjustment strategy to obtain the first test wiring parameter is returned to the execution, until the voltage drop information meets the preset voltage drop condition, the candidate first wiring parameter corresponding to the voltage drop information that meets the preset voltage drop condition is used as the first wiring parameter; The first wiring parameter is evaluated by a physical constraint evaluation strategy to obtain physical constraint evaluation information of the first wiring parameter; Based on the first wiring parameter, the current voltage drop value from the power delivery network to the chip and the current wiring resource utilization rate are identified through the network model, and the voltage wiring evaluation strategy is split into a voltage drop evaluation strategy and a wiring resource evaluation strategy; Based on the current voltage drop value, identifying the voltage drop evaluation result of the first wiring parameter through the voltage drop evaluation strategy, and based on the current wiring resource utilization, identifying the wiring resource evaluation result of the first wiring parameter through the wiring resource evaluation strategy; using the voltage drop evaluation result of the first wiring parameter and the wiring resource evaluation result of the first wiring parameter as the current voltage wiring evaluation result of the first wiring parameter; When the physical constraint evaluation information does not satisfy the physical constraint condition, or the current voltage wiring evaluation result does not satisfy the voltage wiring condition, the first wiring parameter replaces the initial wiring parameter, and returns to the execution in the network model, and adjusts the initial wiring parameter through a simulated annealing algorithm to obtain a first wiring parameter step; Until the physical constraint evaluation information satisfies a preset physical constraint condition and the current voltage wiring evaluation result satisfies a voltage wiring condition, the first wiring parameter is used as a target wiring parameter of the power delivery network.

2. The method according to claim 1, characterized in that The generating, based on the network structure information, a network model of the power delivery network and initial wiring parameters of the network model comprises: Splitting the network structure information of the power transmission network into substructure information of each network structure, and acquiring the structural function of each network structure and the structural connection information of each network structure in the power transmission network database; Based on the substructure information of each network structure, a substructure model of each network structure is constructed respectively through a modeling network, and each substructure model is subjected to model splicing processing through the structural connection information of each network structure to obtain a network structure model of the power transmission network; Based on the structural functions of each of the network structures, generating functional parameters of each of the network structures in the network structure model, and adding the functional parameters of each of the network structures to each of the substructure models of the network structure model to obtain a network model; Collecting historical design information of the power delivery network, and identifying wiring design information in the historical design information; The wiring design information is added to the network model to obtain wiring structure information in the network model, and wiring parameters corresponding to the wiring structure information are identified to obtain initial wiring parameters of the network model.

3. The method according to claim 1, characterized in that: The step of evaluating the first wiring parameter by using a physical constraint evaluation strategy to obtain physical constraint evaluation information of the first wiring parameter includes: Based on the first wiring parameters, in the network model, the wiring information of each wiring condition type from the power delivery network to each metal layer of the chip is identified, and the physical constraint evaluation strategy is split into sub-evaluation strategies of each wiring evaluation angle; In the wiring database, query the wiring evaluation angle corresponding to each wiring condition type, and score the wiring information of each wiring condition type through the sub-evaluation strategy of the wiring evaluation angle corresponding to each wiring condition type to obtain the score value of each wiring condition type; The score value of each type of wiring condition is used as the physical constraint evaluation information of the first wiring parameter.

4. The method according to claim 1, characterized in that After taking the voltage drop evaluation result of the first wiring parameter and the wiring resource evaluation result of the first wiring parameter as the current voltage wiring evaluation result of the first wiring parameter, the method further includes: Obtain physical constraints and voltage wiring conditions; Based on the physical constraint condition, identifying a scoring threshold for each type of wiring condition, and based on the voltage wiring condition, identifying a target voltage drop evaluation result and a target wiring resource evaluation result; When there is a score value of each wiring condition type of the first wiring parameter that is lower than a score threshold of each wiring condition type, determining that the physical constraint evaluation information of the first wiring parameter does not satisfy the physical constraint condition; When the voltage drop evaluation result of the first wiring parameter is different from the target voltage drop evaluation result, or the current voltage wiring evaluation result of the first wiring parameter is different from the target wiring resource evaluation result of the first wiring parameter, it is determined that the current voltage wiring evaluation result of the first wiring parameter does not meet the voltage wiring condition.

5. A device for determining wiring parameters of a power transmission network, characterized in that: The device comprises: An acquisition module, configured to acquire network structure information of a power transmission network, and generate a network model of the power transmission network and initial wiring parameters of the network model based on the network structure information; The processing module is used to adjust the initial wiring parameters through a preset parameter adjustment strategy to obtain a first test wiring parameter, and based on the first test wiring parameter, simulate the power transmission process of the network model to the chip to obtain simulation information; identify the power supply voltage drop value map from the power supply transmission network to the chip in the simulation information through a voltage drop fast evaluator, and identify the wiring resource congestion value map from the power supply transmission network to each metal layer of the chip through a fast router; based on the power supply voltage drop value map and the wiring resource congestion value map, calculate the simulated annealing score value corresponding to the test wiring parameter through a preset first weight value of the power supply voltage drop value map and a preset second weight value of the wiring resource congestion value map, and based on the simulated annealing score value, adjust the first test wiring parameter through a simulated annealing probability algorithm to obtain a second test wiring parameter; replace the initial wiring parameter with the second test wiring parameter, and return to execute the preset parameter. A number adjustment strategy is used to adjust the initial wiring parameters to obtain the first test wiring parameter step, until the preset number of iterations is met, the second test wiring parameters obtained in the last iteration are used as candidate first wiring parameters; based on the candidate first wiring parameters, the voltage drop information from the power supply transmission network to the chip is identified through the network model; when the voltage drop information does not meet the preset voltage drop condition, the initial wiring parameters are replaced by the transmitted candidate first wiring parameters, and the current number of iterations and the preset number of iterations are adjusted, and the execution is returned to adjust the initial wiring parameters through the preset parameter adjustment strategy to obtain the first test wiring parameter step, until the voltage drop information meets the preset voltage drop condition, the candidate first wiring parameters corresponding to the voltage drop information that meets the preset voltage drop condition are used as the first wiring parameters; the first wiring parameters are evaluated and processed through the physical constraint evaluation strategy to obtain the physical constraint evaluation information of the first wiring parameters; An adjustment module is used to identify the current voltage drop value from the power delivery network to the chip and the current wiring resource utilization rate through the network model based on the first wiring parameter, and split the voltage wiring evaluation strategy into a voltage drop evaluation strategy and a wiring resource evaluation strategy; identify the voltage drop evaluation result of the first wiring parameter through the voltage drop evaluation strategy based on the current voltage drop value, and identify the wiring resource evaluation result of the first wiring parameter through the wiring resource evaluation strategy based on the current wiring resource utilization; use the voltage drop evaluation result of the first wiring parameter and the wiring resource evaluation result of the first wiring parameter as the current voltage wiring evaluation result of the first wiring parameter; when the physical constraint evaluation information does not meet the physical constraint condition or the current voltage wiring evaluation result does not meet the voltage wiring condition, replace the initial wiring parameter with the first wiring parameter, return to the execution in the network model, and adjust the initial wiring parameter through the simulated annealing algorithm to obtain the first wiring parameter step; The determination module is configured to use the first wiring parameter as the target wiring parameter of the power delivery network until the physical constraint evaluation information satisfies a preset physical constraint condition and the current voltage wiring evaluation result satisfies a voltage wiring condition.

6. The device according to claim 5, characterized in that The acquisition module is specifically used for: Splitting the network structure information of the power transmission network into substructure information of each network structure, and acquiring the structural function of each network structure and the structural connection information of each network structure in the power transmission network database; Based on the substructure information of each network structure, a substructure model of each network structure is constructed respectively through a modeling network, and each substructure model is subjected to model splicing processing through the structural connection information of each network structure to obtain a network structure model of the power transmission network; Based on the structural functions of each of the network structures, generating functional parameters of each of the network structures in the network structure model, and adding the functional parameters of each of the network structures to each of the substructure models of the network structure model to obtain a network model; Collecting historical design information of the power delivery network, and identifying wiring design information in the historical design information; The wiring design information is added to the network model to obtain wiring structure information in the network model, and wiring parameters corresponding to the wiring structure information are identified to obtain initial wiring parameters of the network model.

7. The device according to claim 5, characterized in that The processing module is specifically used for: Based on the first wiring parameters, in the network model, the wiring information of each wiring condition type from the power delivery network to each metal layer of the chip is identified, and the physical constraint evaluation strategy is split into sub-evaluation strategies of each wiring evaluation angle; In the wiring database, query the wiring evaluation angle corresponding to each wiring condition type, and score the wiring information of each wiring condition type through the sub-evaluation strategy of the wiring evaluation angle corresponding to each wiring condition type to obtain the score value of each wiring condition type; The score value of each type of wiring condition is used as the physical constraint evaluation information of the first wiring parameter.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images