Methods, equipment, chips, and storage media for determining parameters of integrated circuits.

Abstract

This application discloses a method, device, chip, and storage medium for determining parameters of integrated circuits, belonging to the field of data processing technology. The method includes: obtaining a first solution set of a target functional component in the integrated circuit satisfying a multi-objective function; determining two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to each of the n-dimensional optimization points and n-dimensional target optimization points, based on the n-dimensional optimization points and n-dimensional target optimization points; determining boundary two-dimensional optimization points from the two-dimensional optimization points; determining the target value range of each target parameter based on the first parameter values ​​of each boundary two-dimensional optimization point; obtaining a second solution set of the target functional component satisfying the multi-objective function based on the target value range of each target parameter; and determining the target parameter values ​​of at least two target elements based on the second solution set. This method improves the efficiency of target parameter determination while ensuring optimization effectiveness.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a method, apparatus, chip, and storage medium for determining parameters of integrated circuits. Background Technology

[0002] Currently, in the field of integrated circuits, the process of simulating and calculating the parameters of a given integrated circuit to determine the parameter values ​​can be achieved by performing multi-objective optimization calculations after determining the optimization objective. Typically, an initial population is set up, and then parameter combinations of the initial population size are randomly selected within the optimization space. Next, a multi-objective optimization algorithm is used to optimize the objective function. This algorithm can update the population parameters in the direction of the optimization objective, and the two steps of optimization and parameter update are repeated until the program termination condition is met, and the final optimization result is output. Summary of the Invention

[0003] This application provides a method, apparatus, chip, and storage medium for determining parameters of integrated circuits, which can improve the efficiency of target parameter determination. The technical solution is as follows:

[0004] On one hand, embodiments of this application provide a method for determining parameters for integrated circuits, the method comprising:

[0005] Obtain a first solution set of the target functional components in the integrated circuit that satisfy a multi-objective function; the target functional components include at least two target elements; each target element corresponds to a target parameter to be determined; the first solution set contains optimization points obtained after iteration according to a multi-objective optimization algorithm for a first threshold number of times; the optimization points are n-dimensional optimization points distributed in n-dimensional space; n is an integer greater than 1; each optimization point corresponds to a first parameter value of a set of target parameters;

[0006] Based on the n-dimensional optimization points and the n-dimensional target optimization points, determine the two-dimensional optimization points corresponding to each of the n-dimensional optimization points, and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points; the n-dimensional coordinates of the n-dimensional target optimization points correspond to the optimization targets of the target functional components;

[0007] Boundary two-dimensional optimization points are determined from the two-dimensional optimization points; the closed region formed by connecting the boundary two-dimensional optimization points contains the two-dimensional target optimization point.

[0008] Based on the first parameter values ​​of each of the boundary two-dimensional optimization points, the target value range of each of the target parameters is determined;

[0009] Based on the target value range of each of the target parameters, a second solution set is obtained in which the target functional component satisfies the multi-objective function; the second solution set includes the optimization points obtained after a second threshold number of iterations according to the multi-objective optimization algorithm when the search range of the target parameters is the target value range;

[0010] Based on the second solution set, the target parameter values ​​of the target parameters for at least two of the target elements are determined.

[0011] On the other hand, embodiments of this application provide a parameter determination apparatus for integrated circuits, the apparatus comprising:

[0012] The first acquisition module is used to acquire a first solution set of the target functional components in the integrated circuit that satisfy a multi-objective function; the target functional components include at least two target elements; each target element corresponds to a target parameter to be determined; the first solution set includes optimization points obtained after iteration according to a multi-objective optimization algorithm for a first threshold number of times; the optimization points are n-dimensional optimization points distributed in n-dimensional space; n is an integer greater than 1; each optimization point corresponds to a first parameter value of a set of target parameters;

[0013] The optimization point determination module is used to determine, based on the n-dimensional optimization points and the n-dimensional target optimization points, the two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points; the n-dimensional coordinates of the n-dimensional target optimization points correspond to the optimization targets of the target functional components;

[0014] A boundary determination module is used to determine boundary two-dimensional optimization points from the two-dimensional optimization points; the closed region formed by connecting the boundary two-dimensional optimization points contains the two-dimensional target optimization point;

[0015] The range determination module is used to determine the target value range of each of the target parameters based on the first parameter values ​​of each of the boundary two-dimensional optimization points;

[0016] The second acquisition module is used to acquire a second solution set of the target functional component satisfying the multi-objective function based on the target value range of each of the target parameters; the second solution set includes the optimization points obtained after iteration of a second threshold number according to the multi-objective optimization algorithm when the search range of the target parameters is the target value range;

[0017] The target determination module is used to determine the target parameter values ​​of the target parameters of at least two of the target elements based on the second solution set.

[0018] On the other hand, embodiments of this application provide a computer device, the computer device including a processor and a memory; the memory stores at least one computer instruction, the at least one computer instruction being loaded and executed by the processor to implement the parameter determination method for integrated circuits as described above.

[0019] On the other hand, embodiments of this application provide a computer-readable storage medium storing at least one computer instruction, which is loaded and executed by a processor to implement the parameter determination method for integrated circuits as described above.

[0020] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a terminal reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the terminal to perform the parameter determination method for integrated circuits provided in various alternative implementations of the above aspect.

[0021] On the other hand, embodiments of this application provide a chip for executing a parameter determination method for an integrated circuit as described above.

[0022] The beneficial effects of the technical solutions provided in this application include at least the following:

[0023] The computer device performs an initial iterative calculation of the multi-objective function optimization corresponding to the target functional component of the integrated circuit to obtain a first solution set containing each optimization point. Then, based on each optimization point and the target optimization point in the first solution set, the two-dimensional optimization point and the two-dimensional target optimization point in the two-dimensional plane are determined. By determining the positional relationship between the two-dimensional target optimization point and the two-dimensional optimization point in the two-dimensional plane, the search space for the next multi-objective function optimization is determined. This achieves the goal of obtaining a second solution set within a smaller range, avoiding the additional computational burden on the computer device when performing multi-objective function optimization calculations by increasing the population size. While ensuring the optimization effect, it improves the efficiency of determining the target parameters. Attached Figure Description

[0024] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0025] Figure 1 This is a flowchart illustrating an optimization scheme for a multi-objective function according to an exemplary embodiment;

[0026] Figure 2 yes Figure 1 The illustrated embodiment is a schematic diagram of the distribution of the first solution set in three-dimensional space.

[0027] Figure 3 yes Figure 1 The illustrated embodiment is a schematic diagram of the gridded segmentation involved;

[0028] Figure 4 This is a flowchart illustrating a parameter determination method for an integrated circuit according to an exemplary embodiment;

[0029] Figure 5 This is a flowchart illustrating a parameter determination method for an integrated circuit according to an exemplary embodiment;

[0030] Figure 6 yes Figure 5 The illustrated embodiment includes a MOS transistor circuit topology diagram of an operational amplifier.

[0031] Figure 7 This is a structural block diagram of a parameter determination apparatus for an integrated circuit provided in an exemplary embodiment of this application;

[0032] Figure 8 A structural block diagram of a computer device provided in an exemplary embodiment of this application is shown. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0034] In this article, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0035] Subsequent embodiments of this application provide a multi-objective function optimization scheme, which can be applied to scenarios where multi-objective optimization problems are solved using inverse search techniques, and can be applied to multiple fields including the integrated circuit field.

[0036] Please refer to Figure 1 , Figure 1 The flowchart illustrates an optimization scheme for a multi-objective function provided in an exemplary embodiment of this application, as shown below. Figure 1As shown, the computer device can first determine the design objective, namely the multi-objective function and the optimization objective (S101), then set the initial population size used when performing the multi-objective optimization algorithm (S102), then optimize the objective function according to the multi-objective optimization algorithm (S103), update the objective parameters in the population of the current iteration (S104), determine whether the specified number of iterations has been reached (S105), when the number of iterations reaches the specified number of iterations, obtain and output the first solution set of the multi-objective function (S106), otherwise continue to perform iterative calculation according to the multi-objective optimization algorithm; wherein, the multi-objective function contains n objective functions; n is an integer greater than or equal to 2; the n objective functions contain a set of objective parameters to be determined; the first solution set contains the optimization points obtained after the first threshold number of iterations according to the multi-objective optimization algorithm when the value range of the objective parameters is within the first value range; the optimization points are n-dimensional optimization points distributed in n-dimensional space; each optimization point corresponds to a first parameter value of a set of objective parameters; the first parameter value is within the first value range. Determine if the target optimization point is in the first solution set (S107). If the target optimization point is in the first solution set, the multi-objective optimization process is completed. If the target optimization point is not in the first solution set, project the target optimization point and the optimization points in the first solution set onto the same plane (S108). That is, perform dimensionality reduction processing on the n-dimensional optimization points and the n-dimensional target optimization points to obtain the two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points. Then, determine the control range for the next search (S109), that is, determine the boundary two-dimensional optimization points from the two-dimensional optimization points. The closed region formed by connecting the boundary two-dimensional optimization points contains the two-dimensional target optimization points. Based on the boundary two-dimensional optimization points... The first parameter value of each objective parameter is used to determine the second value range of each objective parameter. Then, the objective function is optimized according to a multi-objective optimization algorithm (S110), that is, based on the second value range of each objective parameter, at least one set of second parameter values ​​is determined; the second value range is within the first value range; the second parameter value is within the second value range; the parameter values ​​of the objective parameters in the current iteration population are updated (S111), and it is determined whether the program termination condition is met (S112). This program termination condition can be that the number of iterations reaches a specified number of iterations, or that a target optimization point exists among the optimization points. When the program termination condition is met, the computer device can output the parameter value corresponding to the target optimization point (S113). In other words, based on at least one set of second parameter values, a second solution set of the multi-objective function is obtained; the second solution set contains the optimization points obtained after a second threshold number of iterations according to the multi-objective optimization algorithm when the search range of the objective parameters is within the second value range.

[0037] For example, if the multi-objective function is set to DTLZ2, DTLZ2 can be as follows:

[0038]

[0039]

[0040]

[0041]

[0042] st0≤x i ≤1, i=1,2,3,…,12

[0043] This multi-objective function has three optimization objectives: minimizing f1(x), minimizing f2(x), and minimizing f3(x), and has a total of 12 objective parameters, from x1 to x2. 12 The range of variation is [0,1]. Computer devices can use the NSGAII algorithm to optimize multi-objective functions.

[0044] for example, Figure 2 This is a schematic diagram of the distribution of a first solution set in three-dimensional space, as described in an embodiment of this application. Figure 2 As shown, the first solution set consisting of all optimization points distributed in three-dimensional space can be called the Pareto optimal solution. The optimization points can be relatively evenly distributed on an arc surface. Since the initial population size is 100, the number of optimization points generated in three-dimensional space can also be 100. Due to the small initial population size, there are some blank areas on the arc surface, areas not covered by optimization points. Since the purpose of multi-objective function optimization is to determine the 12 parameter values ​​corresponding to the target optimization point 21, and the current optimization points do not cover the target optimization point 21, it is impossible to obtain the 12 parameter values ​​corresponding to the target optimization point.

[0045] Therefore, for the first solution set in three-dimensional space, the spatial location of the target optimization point can be determined by directional search. First, the three-dimensional optimization points and the target optimization point in the first solution set are projected onto the same two-dimensional plane. Figure 3 This is a schematic diagram of a gridded segmentation method according to an embodiment of this application. For example... Figure 3 As shown, the MPA point cloud algorithm can be used to divide the set of optimization points in the two-dimensional plane into independent triangular regions. The projection of the target optimization point on the two-dimensional plane is the two-dimensional target optimization point 31. The centroid method can be used to find the triangular region where the two-dimensional target optimization point 31 is located, and obtain the 12 parameter values ​​corresponding to the three vertices of the triangular region, i.e., the boundary two-dimensional optimization points 32. The maximum and minimum values ​​of each parameter corresponding to the three boundary two-dimensional optimization points 32 are used as the upper and lower boundaries for the next search. The above scheme can greatly reduce the search space range and improve the search efficiency. Moreover, searching within a smaller space range makes it more likely to find the parameter values ​​corresponding to the target optimization point.

[0046] Figure 4 A flowchart illustrating a parameter determination method for an integrated circuit according to an exemplary embodiment of this application is shown. This parameter determination method for an integrated circuit can be executed by a computer device. The parameter determination method for an integrated circuit includes the following steps:

[0047] Step 401: Obtain the first solution set of the target functional component in the integrated circuit that satisfies the multi-objective function; the target functional component includes at least two target elements; each target element corresponds to a target parameter to be determined; the first solution set contains optimization points obtained after iteration of a first threshold number according to the multi-objective optimization algorithm; the optimization points are n-dimensional optimization points distributed in n-dimensional space; n is an integer greater than 1; each optimization point corresponds to the first parameter value of a set of target parameters.

[0048] In the embodiments of this application, there is a target functional component in the integrated circuit. The target functional component may include at least two target elements. Each of the at least two target elements may correspond to various target parameters to be determined. The computer device may determine the target parameters of each target element through pre-calculation.

[0049] In one possible implementation, when a computer device determines the parameters of each target element of a target functional component in an integrated circuit, it can first determine the multi-objective function that the target functional component needs to satisfy, and after iterative calculation of a first threshold number according to a multi-objective optimization algorithm, it can obtain the first group of optimization points, which can form the first solution set of the multi-objective function.

[0050] Among them, multi-objective optimization algorithm can be a general term for algorithms that optimize multiple objectives simultaneously, including the MOEA / D algorithm and the NSGA-2 algorithm. This algorithm can make multiple objectives as optimal as possible in a given region at the same time. The solution of multi-objective optimization is usually a set of equilibrium solutions (i.e., a set of optimal solutions composed of many Pareto optimal solutions). Each element in the set is called a Pareto optimal solution or a non-dominated optimal solution.

[0051] The first group size can be a pre-set number of optimization points obtained in each iteration of the current objective optimization algorithm; the multi-objective function can be composed of n objective functions, each containing the objective parameters to be determined.

[0052] In one possible implementation, the optimization points calculated by the current multi-objective optimization algorithm can be n-dimensional optimization points distributed in n-dimensional space.

[0053] Since a multi-objective function contains n objective functions, and the optimization objective of each of the n objective functions corresponds to the coordinates of the optimization point in each dimension, the optimization point can be an n-dimensional optimization point distributed in n-dimensional space.

[0054] For example, when the number of the first population is set to a, the multi-objective function includes f(x), g(x), and p(x), and the objective parameters to be determined in f(x), g(x), and p(x) include x. i Let i be an integer greater than or equal to 1 and less than or equal to 12. The optimization direction of each objective function can be the minimum value of f(x), the maximum value of g(x), and p(x) within a specified range. Iterative calculation using a multi-objective optimization algorithm can obtain *a* optimization points that satisfy each optimization direction. These *a* optimization points can be three-dimensional optimization points distributed in three-dimensional space. The coordinates of each three-dimensional optimization point in the three dimensions can be the values ​​of the objective functions f(x), g(x), and p(x), respectively, and each three-dimensional optimization point corresponds to a set of objective parameters x. i The value of is the first parameter value corresponding to each of the 12 target parameters for each three-dimensional optimization point.

[0055] Step 402: Based on the n-dimensional optimization points and the n-dimensional target optimization points, determine the two-dimensional optimization points corresponding to each of the n-dimensional optimization points, and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points; the n-dimensional coordinates of the n-dimensional target optimization points correspond to the optimization targets of the target functional components.

[0056] In this embodiment of the application, after obtaining the first solution set, the computer device can process each optimization point in the first solution set and the predetermined target optimization point to obtain the two-dimensional optimization point corresponding to each optimization point and the two-dimensional target optimization point corresponding to the target optimization point.

[0057] In this context, the n-dimensional coordinates of the n-dimensional target optimization point correspond to the optimization target of the target functional component. In other words, a target optimization point can be pre-generated by computer equipment or pre-set by professionals as the optimization target of the target functional component.

[0058] For example, if the multi-objective function includes f(x), g(x), and p(x), and the optimization direction of each objective function can be the minimum value of f(x), the maximum value of g(x), and p(x) within a specified range, the optimization objectives of the objective functional components can also be set as f(x) = b, g(x) = c, and p(x) = d. The coordinates of the three-dimensional objective optimization points distributed in three-dimensional space are (b, c, d), and the coordinates of the two-dimensional objective optimization points corresponding to the three-dimensional objective optimization points can be (b, c), (b, d), or (c, d).

[0059] Step 403: Determine the boundary two-dimensional optimization points from the two-dimensional optimization points; the closed region formed by connecting the boundary two-dimensional optimization points contains the two-dimensional target optimization points.

[0060] In this embodiment of the application, the computer device determines boundary two-dimensional optimization points from the acquired two-dimensional optimization points, and the closed region formed by connecting the boundary two-dimensional optimization points may contain two-dimensional target optimization points.

[0061] In one possible implementation, the boundary two-dimensional optimization point can be at least three two-dimensional optimization points. When the boundary two-dimensional optimization point is three two-dimensional optimization points, the triangular region enclosed by the three two-dimensional optimization points can contain the two-dimensional target optimization point.

[0062] Step 404: Based on the first parameter values ​​of each of the boundary two-dimensional optimization points, determine the target value range of each target parameter.

[0063] In this embodiment of the application, the computer device can determine the target value range for each target parameter when performing the next multi-objective optimization algorithm based on the first parameter value of each target parameter of each boundary two-dimensional optimization point.

[0064] For example, if three boundary two-dimensional optimization points are obtained, namely boundary optimization point 1, boundary optimization point 2, and boundary optimization point 3, and the target parameter x corresponding to each optimization point is... i Where i is an integer greater than or equal to 1 and less than or equal to 3, meaning that each optimization point corresponds to three objective parameters. The objective parameters corresponding to boundary optimization point 1 are x1 = e, x2 = h, and x3 = j; the objective parameters corresponding to boundary optimization point 2 are x1 = k, x2 = l, and x3 = m; and the objective parameters corresponding to boundary optimization point 3 are x1 = o, x2 = q, and x3 = r. Therefore, it can be determined that the target value range of objective parameter x1 is greater than the minimum value among e, k, and o, and less than the maximum value among e, k, and o; the target value range of objective parameter x2 is greater than the minimum value among h, l, and q, and less than the maximum value among h, l, and q; and the target value range of objective parameter x3 is greater than the minimum value among j, m, and r, and less than the maximum value among j, m, and r.

[0065] Step 405: Based on the target value range of each target parameter, obtain the second solution set of the target functional component that satisfies the multi-objective function; the second solution set includes the optimization points obtained after the second threshold number of iterations according to the multi-objective optimization algorithm when the search range of the target parameter is the target value range.

[0066] In this embodiment of the application, the computer device can obtain the second solution set of the target functional component satisfying the multi-objective function according to the target value range of each target parameter.

[0067] The second solution set may include all optimization points that can be obtained after iterative calculation of the second threshold number of times according to the multi-objective optimization algorithm when the search range of the objective parameter is determined to be the target value range.

[0068] In one possible implementation, when performing the current multi-objective optimization algorithm, the number of the second population can be set to s, which can be the same as or different from the number of the first population.

[0069] Because the search range is narrowed to a certain extent, the computer can determine the final optimization point with an error of less than a specified threshold without acquiring a large number of optimization points. Therefore, the number of the second group can be set to be less than the number of the first group, which can reduce the computational burden of the computer to a certain extent without affecting the accuracy of the final determined parameters.

[0070] Step 406: Based on the second solution set, determine the target parameter values ​​of the target parameters for at least two target elements.

[0071] In this embodiment of the application, after the computer device obtains the second solution set, it can obtain an optimization point from the second solution set and determine the parameter values ​​of each target parameter corresponding to the optimization point as the target parameter values ​​of the target parameters of at least two target elements.

[0072] In one possible implementation, if a target optimization point exists in the second solution set, the parameter values ​​of each target parameter corresponding to the target optimization point are determined as the target parameter values ​​of the target parameters of at least two target elements; if no target optimization point exists in the second solution set, the parameter values ​​of each target parameter corresponding to the optimization point closest to the target optimization point in the second solution set are determined as the target parameter values ​​of the target parameters of at least two target elements.

[0073] When there is no target optimization point in the second solution set, the optimization point with the smallest error between the second solution set and the target optimization point can be determined as the final output optimization point, and the parameter values ​​of each target parameter corresponding to the optimization point can be determined as the target parameter values ​​of the target parameters of at least two target elements.

[0074] In summary, in this embodiment, the computer device performs an initial iterative calculation of the multi-objective function optimization corresponding to the target functional component of the integrated circuit to obtain a first solution set containing each optimization point. Then, based on each optimization point and the target optimization point in the first solution set, it determines the two-dimensional optimization point and the two-dimensional target optimization point in the two-dimensional plane. By determining the positional relationship between the two-dimensional target optimization point and the two-dimensional optimization point in the two-dimensional plane, it determines the search space for the next multi-objective function optimization, thereby achieving the goal of obtaining a second solution set within a smaller range. This avoids the additional computational burden on the computer device caused by increasing the population size when performing multi-objective function optimization calculations, and improves the efficiency of determining the target parameters while ensuring the optimization effect.

[0075] Figure 5 A flowchart illustrating a parameter determination method for an integrated circuit according to an exemplary embodiment of this application is shown. This parameter determination method for an integrated circuit can be executed by a computer device. The parameter determination method for an integrated circuit includes the following steps:

[0076] Step 501: Obtain the first solution set of the target functional component in the integrated circuit that satisfies the multi-objective function.

[0077] In this embodiment of the application, during the integrated circuit design phase, the computer device needs to perform optimization simulations on each functional component in the integrated circuit to determine the optimized parameters of each element in each functional component. Therefore, for a target functional component in the integrated circuit, the first solution set of the target functional component satisfying a multi-objective function can be obtained first.

[0078] The target functional component includes at least two target elements; each target element corresponds to a target parameter to be determined; the first solution set contains optimization points obtained after iterations of a first threshold number according to a multi-objective optimization algorithm; the optimization points are n-dimensional optimization points distributed in n-dimensional space; n is an integer greater than 1; each optimization point corresponds to the first parameter value of a set of target parameters.

[0079] For example, if the target functional component is an operational amplifier in an integrated circuit, the target elements in the target functional component can be the individual transistors in the operational amplifier; the target parameters to be determined for each target element can be the length and width dimensions, resistance value, and capacitance value of each transistor, etc.

[0080] for example, Figure 6 This is a MOS transistor circuit topology diagram of an operational amplifier according to an embodiment of this application. Figure 6 As shown, T1-T8 are the numbers for each transistor. The circuit design parameters, which correspond to the target parameters above, are the length and width dimensions, resistance, and capacitance values ​​for each transistor.

[0081] To optimize the operational amplifier, a multi-objective function and optimization objective can be predefined. The optimization objective can be to maximize the gain, maximize the gain-bandwidth product (Ft), minimize the quiescent current (Iq), and ensure that the phase margin is within a suitable range.

[0082] Among them, gain is an important indicator of an amplifier's amplification capability, and its unit is decibels (dB); the gain-bandwidth product (Ft) is an indicator of the amplifier's frequency response; the frequency value corresponding to a gain of 0dB is the gain-bandwidth product; quiescent current (Iq) refers to the current consumed by the circuit itself when there is no signal input, and the quiescent power consumption of the circuit can be calculated based on this quiescent current value; phase margin is a parameter that can measure the stability of an operational amplifier, referring to the difference between the phase of the operational amplifier when the open-loop gain is 0dB and 180°, theoretically it should be greater than -π, but it is usually used... To allow for some margin; additionally, the objective function included in a multi-objective function can be as follows:

[0083] max Gain

[0084] max Ft

[0085] min Iq

[0086]

[0087] The computer equipment is set to a first group size, i.e., the number of the first group is 100, and a first threshold number, i.e. the first iteration number is 10. According to the multi-objective optimization algorithm, after 10 iterations, the first solution set, i.e. the Pareto solution set, can be output.

[0088] In one possible implementation, if the first solution set does not include the target optimization point, the following steps can be performed; if the first solution set includes the target optimization point, the first parameter value of the target parameter corresponding to the target optimization point is directly determined as the target parameter value.

[0089] In one possible implementation, in response to the fact that the first solution set does not include the n-dimensional target optimization point, the n-dimensional optimization point and the n-dimensional target optimization point are dimensionality reduced to obtain the two-dimensional optimization point corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization point corresponding to the n-dimensional target optimization point.

[0090] Step 502: Dimensionality reduction is performed on the n-dimensional optimization points and the n-dimensional target optimization points to obtain the two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points.

[0091] In this embodiment of the application, in response to n being an integer greater than 2, the computer device performs dimensionality reduction processing on the n-dimensional optimization points to obtain their respective two-dimensional optimization points and two-dimensional target optimization points.

[0092] In one possible implementation, the n-dimensional optimization points and the n-dimensional target optimization points are projected onto the same two-dimensional plane to obtain the two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points.

[0093] For example, if a professional needs to determine the parameter values ​​of the target element in a target functional component according to Gain = 50dB and Ft = 15MHz, then the two-dimensional target optimization point can be determined to be the optimization point with coordinates (50, 15) on the Gain-Ft plane. Projecting each three-dimensional optimization point in the first solution set onto the Gain-Ft plane yields the two-dimensional optimization point on the Gain-Ft dimension corresponding to each three-dimensional optimization point.

[0094] In one possible implementation, when n equals 3, the first solution set contains three-dimensional optimization points, and each three-dimensional optimization point in the first solution set can be directly reduced to its corresponding two-dimensional optimization point through projection. However, when n is greater than 3, the multi-dimensional optimization points contained in the first solution set need to be reduced to two-dimensional optimization points through permutation and combination, and the two-dimensional optimization points obtained by the dimensionality reduction method under each case are obtained.

[0095] In response to the fact that the optimization points are distributed in three-dimensional space, the three-dimensional optimization points and the three-dimensional target optimization points are projected onto the same two-dimensional plane to obtain the two-dimensional optimization points corresponding to each of the three-dimensional optimization points and the two-dimensional target optimization points corresponding to the three-dimensional target optimization points.

[0096] In addition, in response to n being an integer greater than 3, the various three-dimensional spaces contained in the n-dimensional space are determined by permutation and combination; the three-dimensional optimization points corresponding to the n-dimensional optimization points and the three-dimensional target optimization points in the same three-dimensional space are projected onto the same two-dimensional plane to obtain the two-dimensional optimization points corresponding to the three-dimensional optimization points in each three-dimensional space, and the two-dimensional target optimization points corresponding to the three-dimensional target optimization points.

[0097] For example, for optimization points distributed in four-dimensional space, or even higher-dimensional multi-objective optimization backsearch problems, all combinations of three-dimensional space can be listed. For instance, if the optimization points in the first solution set are distributed in five-dimensional space, there are a total of... The combination of dimensionality reduction to three-dimensional space is used. The optimization points in the first solution set are reduced to 10 three-dimensional spaces respectively and projected onto the same two-dimensional plane to obtain the two-dimensional optimization points corresponding to each optimization point in the first solution set.

[0098] Step 503: Determine the boundary two-dimensional optimization points from the two-dimensional optimization points.

[0099] In this embodiment of the application, after the computer device obtains each two-dimensional optimization point in the first solution set, it can determine the boundary two-dimensional optimization point from each two-dimensional optimization point. The closed region formed by connecting the boundary two-dimensional optimization points contains the two-dimensional target optimization point.

[0100] In one possible implementation, based on the two-dimensional optimization point, the two-dimensional plane is divided into various triangular ranges, and the three vertices of the triangular range that includes the two-dimensional target optimization point and has the smallest area are determined as the boundary two-dimensional optimization point.

[0101] The triangle range can be defined by three 2D optimization points as vertices, and the triangle range does not include other 2D optimization points.

[0102] For example, a computer device can utilize the MPA point cloud meshing algorithm to divide the Gain-Ft plane into independent triangular regions with the two-dimensional optimization points as vertices, based on the two-dimensional optimization points projected onto the Gain-Ft plane from each optimization point in the first solution set. It then determines which triangular region the target optimization point (Gain = 50dB, Ft = 15MHz) is located in. The maximum and minimum values ​​of each target parameter corresponding to the three vertices of the triangular region where the target optimization point is located can be used as the upper and lower boundaries for subsequent searches. The MPA point cloud meshing algorithm can be an algorithm that divides a planar point set into multiple independent triangular regions.

[0103] Among these methods, computer equipment can use the centroid method to determine the triangular region where the target optimization point is located. The centroid method is an algorithm for determining whether a point is inside a triangle in space.

[0104] Step 504: Based on the first parameter values ​​of each of the boundary two-dimensional optimization points, determine the target value range of each target parameter.

[0105] In one possible implementation, the first parameter value of the i-th objective parameter of each boundary two-dimensional optimization point is obtained; the maximum value among the first parameter values ​​of the i-th objective parameter is determined as the upper limit of the second value range of the i-th objective parameter; the minimum value among the first parameter values ​​of the i-th objective parameter is determined as the lower limit of the second value range of the i-th objective parameter; based on the upper limit of the second value range of the i-th objective parameter and the lower limit of the second value range of the i-th objective parameter, the second value range of the i-th objective parameter is determined.

[0106] For example, when a computer device uses the MPA point cloud meshing algorithm to determine the triangular region where the target optimization point is located, and determines the three vertices of the triangular region as boundary two-dimensional optimization points, the maximum and minimum values ​​of each target parameter corresponding to the three vertices can be used as the upper and lower boundary values ​​for the next search, and the target value range of each target parameter can be obtained in this way.

[0107] Step 505: Based on the target value range of each target parameter, obtain the second solution set of the target functional component that satisfies the multi-objective function.

[0108] In this embodiment of the application, the computer device assigns values ​​to each target parameter according to the target value range of each target parameter, and obtains a second solution set of the target functional component that satisfies the multi-objective function.

[0109] The multi-objective function can be the same as the objective function set when performing the multi-objective optimization algorithm for the first time, and a second population size, i.e., the number of second populations, and a second threshold number, i.e., the number of second iterations, can be set.

[0110] The size of the second population can be the same as or different from that of the first population, and the number of times the second threshold can be the same as or different from that of the first threshold.

[0111] Because the search range was narrowed during the second multi-objective optimization algorithm, the number of the second population and the number of times the second threshold was applied can be reduced during the second multi-objective optimization algorithm, thereby reducing the computational burden on the computer while ensuring the efficiency of parameter determination.

[0112] In one possible implementation, based on the target value range of each target parameter, at least one set of second parameter values ​​for each target parameter is determined; based on the at least one set of second parameter values ​​for each target parameter, a second solution set satisfying the multi-objective function for the target functional component is obtained.

[0113] For example, when performing the multi-objective optimization algorithm again, the second population size can be set to 10, the second iteration number to 50, and the multi-objective optimization algorithm can be used for iterative calculation. After the iteration is completed, the second solution set can be output, which may include 10 optimization points that are closest to the target optimization point.

[0114] Step 506: Based on the second solution set, determine the target parameter values ​​of the target parameters for at least two target elements.

[0115] In this embodiment of the application, after obtaining the second solution set, the computer device can determine an optimization point with the smallest error from the second solution set by calculation, and determine the second parameter value of the target parameter corresponding to the optimization point with the smallest error as the parameter value of the target parameter of each target element in the target functional component, thereby completing the parameter determination of the target element.

[0116] For example, a computer device can determine the error percentage corresponding to each optimization point in the second solution set using an error calculation formula, output the optimization point with the smallest error percentage, and determine the second parameter value of the target parameter corresponding to that optimization point as the parameter value of the target element in the target functional component. The formula for calculating this error percentage can be...

[0117]

[0118] Wherein, Gain′ is the gain calculated based on the second parameter values ​​of each objective parameter corresponding to the two-dimensional optimization point in the second solution set, and Ft′ is the gain-bandwidth product calculated based on the second parameter values ​​of each objective parameter corresponding to the two-dimensional optimization point in the second solution set.

[0119] In summary, in this embodiment, the computer device performs an initial iterative calculation of the multi-objective function optimization corresponding to the target functional component of the integrated circuit to obtain a first solution set containing each optimization point. Then, based on each optimization point and the target optimization point in the first solution set, it determines the two-dimensional optimization point and the two-dimensional target optimization point in the two-dimensional plane. By determining the positional relationship between the two-dimensional target optimization point and the two-dimensional optimization point in the two-dimensional plane, it determines the search space for the next multi-objective function optimization, thereby achieving the goal of obtaining a second solution set within a smaller range. This avoids the additional computational burden on the computer device caused by increasing the population size when performing multi-objective function optimization calculations, and improves the efficiency of determining the target parameters while ensuring the optimization effect.

[0120] Figure 7 A structural block diagram of a parameter determination apparatus for integrated circuits provided in an exemplary embodiment of this application is shown. The parameter determination apparatus for integrated circuits includes:

[0121] The first acquisition module 710 is used to acquire a first solution set of the target functional components in the integrated circuit that satisfy a multi-objective function; the target functional components include at least two target elements; each target element corresponds to a target parameter to be determined; the first solution set includes optimization points obtained after iteration according to a multi-objective optimization algorithm and a first threshold number of iterations; the optimization points are n-dimensional optimization points distributed in n-dimensional space; n is an integer greater than 1; each optimization point corresponds to a first parameter value of a set of target parameters;

[0122] The optimization point determination module 720 is used to determine, based on the n-dimensional optimization points and the n-dimensional target optimization points, the two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points; the n-dimensional coordinates of the n-dimensional target optimization points correspond to the optimization targets of the target functional components.

[0123] The boundary determination module 730 is used to determine boundary two-dimensional optimization points from the two-dimensional optimization points; the closed region formed by connecting the boundary two-dimensional optimization points contains the two-dimensional target optimization point;

[0124] The range determination module 740 is used to determine the target value range of each of the target parameters based on the first parameter values ​​of each of the boundary two-dimensional optimization points;

[0125] The second acquisition module 750 is used to acquire a second solution set of the target functional component satisfying the multi-objective function based on the target value range of each of the target parameters; the second solution set includes the optimization points obtained after iteration of a second threshold number according to the multi-objective optimization algorithm when the search range of the target parameters is the target value range;

[0126] The target determination module 760 is used to determine the target parameter values ​​of the target parameters of at least two of the target elements based on the second solution set.

[0127] In one possible implementation, in response to n being an integer greater than 2, the optimization point determination module 720 includes:

[0128] The n-dimensional optimization points and the n-dimensional target optimization points are reduced in dimensionality to obtain the two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points.

[0129] In one possible implementation, the optimization point determination module 720 further includes:

[0130] Projecting the n-dimensional optimization points and the n-dimensional target optimization points onto the same two-dimensional plane yields the two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to each of the n-dimensional target optimization points.

[0131] In one possible implementation, the optimization point determination module 720 further includes:

[0132] In response to the fact that the optimization points are distributed in three-dimensional space, the three-dimensional optimization points and the three-dimensional target optimization points are projected onto the same two-dimensional plane to obtain the two-dimensional optimization points corresponding to each of the three-dimensional optimization points and the two-dimensional target optimization points corresponding to each of the three-dimensional target optimization points.

[0133] In one possible implementation, the optimization point determination module 720 further includes:

[0134] In response to the fact that n is an integer greater than 3, the various three-dimensional spaces contained in the n-dimensional space are determined by permutation and combination;

[0135] The three-dimensional optimization points and the three-dimensional target optimization points corresponding to the n-dimensional optimization points in the same three-dimensional space are projected onto the same two-dimensional plane to obtain the two-dimensional optimization points corresponding to the three-dimensional optimization points in each three-dimensional space, and the two-dimensional target optimization points corresponding to the three-dimensional target optimization points.

[0136] In one possible implementation, the optimization point determination module 720 further includes:

[0137] In response to the fact that the first solution set does not include the n-dimensional target optimization point, the n-dimensional optimization point and the n-dimensional target optimization point are subjected to dimensionality reduction processing to obtain the two-dimensional optimization point corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization point corresponding to the n-dimensional target optimization point.

[0138] In one possible implementation, the boundary determination module 730 includes:

[0139] Based on the two-dimensional optimization points, the two-dimensional plane is divided into various triangular ranges; each triangular range is defined by three of the two-dimensional optimization points as vertices, and the triangular range does not include any other two-dimensional optimization points.

[0140] The three vertices of the triangle range that includes the two-dimensional target optimization point and has the smallest area are determined as the boundary two-dimensional optimization point.

[0141] In one possible implementation, the range determination module 740 includes:

[0142] Obtain the first parameter value of the i-th objective parameter for each of the two-dimensional optimization points on the boundary;

[0143] The maximum value among the first parameter values ​​of the i-th target parameter is determined as the upper limit of the second value range of the i-th target parameter;

[0144] The minimum value among the first parameter values ​​of the i-th target parameter is determined as the lower limit of the second value range of the i-th target parameter;

[0145] The target value range of the i-th target parameter is determined based on the upper limit of the second value range of the i-th target parameter and the lower limit of the second value range of the i-th target parameter.

[0146] In one possible implementation, the second acquisition module 750 includes:

[0147] Based on the target value range of each of the target parameters, at least one set of second parameter values ​​for each of the target parameters is determined;

[0148] Based on the second parameter values ​​of at least one set of each of the target parameters, a second solution set is obtained in which the target functional component satisfies the multi-objective function.

[0149] In summary, in this embodiment, the computer device performs an initial iterative calculation of the multi-objective function optimization corresponding to the target functional component of the integrated circuit to obtain a first solution set containing each optimization point. Then, based on each optimization point and the target optimization point in the first solution set, it determines the two-dimensional optimization point and the two-dimensional target optimization point in the two-dimensional plane. By determining the positional relationship between the two-dimensional target optimization point and the two-dimensional optimization point in the two-dimensional plane, it determines the search space for the next multi-objective function optimization, thereby achieving the goal of obtaining a second solution set within a smaller range. This avoids the additional computational burden on the computer device caused by increasing the population size when performing multi-objective function optimization calculations, and improves the efficiency of determining the target parameters while ensuring the optimization effect.

[0150] Figure 8 This illustration shows a structural block diagram of a computer device provided in an exemplary embodiment of this application. The computer device may be an electronic device such as a smartphone, tablet computer, e-reader, portable personal computer, or smart wearable device. The computer device in this application may include one or more of the following components: a processor 810, a memory 820, and a screen 830.

[0151] The processor 810 may include one or more processing cores. The processor 810 connects to various parts of the terminal using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 820, and by calling data stored in the memory 820. Optionally, the processor 810 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 810 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen 830; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 810 and may be implemented separately using a communication chip.

[0152] The memory 820 may include random access memory (RAM) or read-only memory (ROM). Optionally, the memory 820 may include a non-transitory computer-readable storage medium. The memory 820 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 820 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), instructions for implementing the various method embodiments described above, etc. The operating system may be an Android system (including systems deeply developed based on the Android system), an iOS system developed by Apple Inc. (including systems deeply developed based on the iOS system), or other systems. The data storage area may also store data created by the terminal during use (such as phonebook data, audio and video data, chat history data, etc.).

[0153] In addition, those skilled in the art will understand that the structure of the computer device shown in the above figures does not constitute a limitation on the computer device. The computer device may include more or fewer components than shown, or combine certain components, or have different component arrangements. For example, the terminal may also include radio frequency circuits, imaging components, sensors, audio circuits, Wireless Fidelity (WiFi) components, power supplies, Bluetooth components, etc., which will not be described in detail here.

[0154] This application also provides a computer-readable storage medium storing at least one computer instruction, which is loaded and executed by a processor to implement the parameter determination method for integrated circuits as described in the above embodiments.

[0155] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a terminal reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the terminal to perform the parameter determination method for integrated circuits provided in various alternative implementations of the above aspect.

[0156] This application also provides a chip for executing the parameter determination method for integrated circuits as described in the above embodiments.

[0157] Those skilled in the art will recognize that the functions described in the embodiments of this application in one or more of the above examples can be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable storage medium or transmitted as one or more instructions or code on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of a computer program from one place to another. Storage media can be any available medium accessible to a general-purpose or special-purpose computer.

[0158] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining parameters for integrated circuits, characterized in that, The method includes: Obtain a first solution set of the target functional components in the integrated circuit that satisfy a multi-objective function; the target functional components include at least two target elements; each target element corresponds to a target parameter to be determined; the first solution set contains optimization points obtained after iteration according to a multi-objective optimization algorithm for a first threshold number of times; the optimization points are n-dimensional optimization points distributed in n-dimensional space; n is an integer greater than 1; each optimization point corresponds to a first parameter value of a set of target parameters; Based on the n-dimensional optimization points and the n-dimensional target optimization points, determine the two-dimensional optimization points corresponding to each of the n-dimensional optimization points, and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points; the n-dimensional coordinates of the n-dimensional target optimization points correspond to the optimization targets of the target functional components; Boundary two-dimensional optimization points are determined from the two-dimensional optimization points; the closed region formed by connecting the boundary two-dimensional optimization points contains the two-dimensional target optimization point. Based on the first parameter values ​​of each of the boundary two-dimensional optimization points, the target value range of each of the target parameters is determined; Based on the target value range of each of the target parameters, a second solution set is obtained in which the target functional component satisfies the multi-objective function; the second solution set includes the optimization points obtained after a second threshold number of iterations according to the multi-objective optimization algorithm when the search range of the target parameters is the target value range; Based on the second solution set, the target parameter values ​​of the target parameters for at least two of the target elements are determined.

2. The method according to claim 1, characterized in that, In response to the fact that n is an integer greater than 2; the step of determining the two-dimensional optimization point corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization point corresponding to the n-dimensional target optimization point based on the n-dimensional optimization points and the n-dimensional target optimization point includes: The n-dimensional optimization points and the n-dimensional target optimization points are reduced in dimensionality to obtain the two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points.

3. The method according to claim 2, characterized in that, The step of reducing the dimensionality of the n-dimensional optimization points and the n-dimensional target optimization points to obtain the two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points includes: Project the n-dimensional optimization points and the n-dimensional target optimization points onto the same two-dimensional plane to obtain the two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to each of the n-dimensional target optimization points.

4. The method according to claim 3, characterized in that, The step of projecting the n-dimensional optimization points and the n-dimensional target optimization points onto the same two-dimensional plane to obtain the two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points includes: In response to the fact that the optimization points are distributed in three-dimensional space, the three-dimensional optimization points and the three-dimensional target optimization points are projected onto the same two-dimensional plane to obtain the two-dimensional optimization points corresponding to each of the three-dimensional optimization points and the two-dimensional target optimization points corresponding to each of the three-dimensional target optimization points.

5. The method according to claim 3, characterized in that, The step of projecting the n-dimensional optimization points and the n-dimensional target optimization points onto the same two-dimensional plane to obtain the two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points includes: In response to the fact that n is an integer greater than 3, the various three-dimensional spaces contained in the n-dimensional space are determined by permutation and combination; The three-dimensional optimization points and the three-dimensional target optimization points corresponding to the n-dimensional optimization points in the same three-dimensional space are projected onto the same two-dimensional plane to obtain the two-dimensional optimization points corresponding to the three-dimensional optimization points in each three-dimensional space, and the two-dimensional target optimization points corresponding to the three-dimensional target optimization points.

6. The method according to claim 2, characterized in that, The step of reducing the dimensionality of the n-dimensional optimization points and the n-dimensional target optimization points to obtain the two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points includes: In response to the fact that the first solution set does not include the n-dimensional target optimization point, the n-dimensional optimization point and the n-dimensional target optimization point are subjected to dimensionality reduction processing to obtain the two-dimensional optimization point corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization point corresponding to the n-dimensional target optimization point.

7. The method according to claim 1, characterized in that, Determining the boundary two-dimensional optimization point from the two-dimensional optimization points includes: Based on the two-dimensional optimization points, the two-dimensional plane is divided into various triangular ranges; each triangular range is defined by three of the two-dimensional optimization points as vertices, and the triangular range does not include any other two-dimensional optimization points. The three vertices of the triangle containing the two-dimensional target optimization point and having the smallest area are determined as the boundary two-dimensional optimization point.

8. The method according to claim 1, characterized in that, The step of determining the target value range of each target parameter based on the first parameter value of each of the boundary two-dimensional optimization points includes: Obtain the first parameter value of the i-th objective parameter for each of the two-dimensional optimization points on the boundary; The maximum value among the first parameter values ​​of the i-th target parameter is determined as the upper limit of the second value range of the i-th target parameter; The minimum value among the first parameter values ​​of the i-th target parameter is determined as the lower limit of the second value range of the i-th target parameter; The target value range of the i-th target parameter is determined based on the upper limit of the second value range of the i-th target parameter and the lower limit of the second value range of the i-th target parameter.

9. The method according to claim 1, characterized in that, The step of obtaining a second solution set of the target functional component satisfying the multi-objective function based on the target value range of each of the target parameters includes: Based on the target value range of each of the target parameters, at least one set of second parameter values ​​for each of the target parameters is determined; Based on the second parameter values ​​of at least one set of each of the target parameters, a second solution set is obtained in which the target functional component satisfies the multi-objective function.

10. A parameter determination device for integrated circuits, characterized in that, The device includes: The first acquisition module is used to acquire a first solution set of the target functional components in the integrated circuit that satisfy a multi-objective function; the target functional components include at least two target elements; each target element corresponds to a target parameter to be determined; the first solution set includes optimization points obtained after iteration according to a multi-objective optimization algorithm for a first threshold number of times; the optimization points are n-dimensional optimization points distributed in n-dimensional space; n is an integer greater than 1; each optimization point corresponds to a first parameter value of a set of target parameters; The optimization point determination module is used to determine, based on the n-dimensional optimization points and the n-dimensional target optimization points, the two-dimensional optimization points corresponding to each of the n-dimensional optimization points and the two-dimensional target optimization points corresponding to the n-dimensional target optimization points; the n-dimensional coordinates of the n-dimensional target optimization points correspond to the optimization targets of the target functional components; A boundary determination module is used to determine boundary two-dimensional optimization points from the two-dimensional optimization points; the closed region formed by connecting the boundary two-dimensional optimization points contains the two-dimensional target optimization point; The range determination module is used to determine the target value range of each of the target parameters based on the first parameter values ​​of each of the boundary two-dimensional optimization points; The second acquisition module is used to acquire a second solution set of the target functional component satisfying the multi-objective function based on the target value range of each of the target parameters; the second solution set includes the optimization points obtained after iteration of a second threshold number according to the multi-objective optimization algorithm when the search range of the target parameters is the target value range; The target determination module is used to determine the target parameter values ​​of the target parameters of at least two of the target elements based on the second solution set.

11. A computer device, characterized in that, The computer device includes a processor and a memory; the memory stores at least one computer instruction, which is loaded and executed by the processor to implement the parameter determination method for integrated circuits as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer instruction, which is loaded and executed by a processor to implement the parameter determination method for integrated circuits as described in any one of claims 1 to 9.

13. A computer program product, characterized in that, The computer program product includes computer instructions that are executed by a processor of a terminal, causing the terminal to perform the parameter determination method for integrated circuits as described in any one of claims 1 to 9.

14. A chip, characterized in that, The chip is used to perform the parameter determination method for integrated circuits as described in any one of claims 1 to 9.

Images