Industrial simulation all-in-one machine performance evaluation method, device, server and storage medium

Abstract

The present invention belongs to the technical field of performance evaluation of industrial simulation integrated machines, and specifically relates to a performance evaluation method, device, server and storage medium for industrial simulation integrated machines. The method comprises: obtaining an overall range of an industrial simulation integrated machine to be evaluated and decomposing it into N key modules; matching a benchmark whole corresponding to the overall range, updating the benchmark whole, obtaining multiple transition wholes and the whole to be evaluated, and performing performance tests in sequence to obtain bottleneck key modules; outputting an evaluation report based on the test results of the industrial simulation integrated machine to be evaluated, the test results of the N key modules and the bottleneck key modules; the present invention can be used to realize vertical decomposition of the performance of the industrial simulation integrated machine, so that the overall performance of the integrated machine maintains a certain correlation with the performance of each key module on the vertical technology stack, and decomposing the overall performance indicators of the integrated machine into the performance indicators of each key module, so as to more accurately locate the performance bottleneck.

Description

Technical Field

[0001] The present invention belongs to the technical field of industrial simulation all-in-one machine performance evaluation, and specifically relates to an industrial simulation all-in-one machine performance evaluation method, device, server and storage medium. Background Art

[0002] The combination of industrial software, server operating system and server hardware is usually called an industrial simulation all-in-one machine. The performance tuning of an industrial simulation all-in-one machine is a highly professional job, which requires the joint efforts of domestic industrial simulation software, domestic server operating system, domestic server hardware and mathematical library middleware to complete performance optimization.

[0003] The current method of locating the performance bottleneck of industrial simulation all-in-one machines is divided into two stages: the first stage is to determine the performance gap by comparing the full-stack domestic industrial simulation all-in-one machine with the international benchmark platform all-in-one machine; the second stage is to compare the industrial simulation software, server operating system and server hardware separately. This method has the following defects: (1) There is no clear correlation between the overall performance comparison in stage one and the performance comparison of each module in stage two, which cannot guide performance tuning from an overall perspective; (2) The results obtained by the method of comparing the industrial simulation software, server operating system and server hardware separately have large errors, which makes it impossible to locate the specific bottleneck of the all-in-one machine. Summary of the invention

[0004] In order to overcome the shortcomings of the prior art, the present invention provides an industrial simulation all-in-one performance evaluation method, device, server and storage medium to solve the problem that the prior art method of locating performance bottlenecks lacks a clear correlation between the overall performance comparison in stage one and the performance comparison of each module in stage two, and cannot guide performance tuning from an overall perspective.

[0005] One solution of the present invention provides a method for evaluating the performance of an industrial simulation integrated machine, comprising:

[0006] Obtaining the overall scope of the industrial simulation integrated machine to be evaluated, and decomposing the overall scope into N key modules based on the vertical stack information of the industrial simulation integrated machine to be evaluated;

[0007] Matching a reference whole corresponding to the whole range, updating the reference whole by using the N key modules with a preset update strategy, and obtaining N-1 transitional wholes and 1 whole to be evaluated;

[0008] Performing performance tests on the benchmark entity, N-1 transition entities, and the entity to be evaluated in sequence to obtain test results of the entity to be evaluated and the N-1 transition entities;

[0009] Arrange the N key modules in ascending order based on the test results to obtain the bottleneck key module;

[0010] Based on the test results of the industrial simulation integrated machine to be evaluated, the test results of the N key modules and the bottleneck key module, an evaluation report is output.

[0011] In this solution, the performance evaluation method of the industrial simulation all-in-one machine can be used to achieve vertical decomposition of the performance of the industrial simulation all-in-one machine, so that the overall performance of the all-in-one machine maintains a certain correlation with the performance of each key module on the vertical technology stack. Through this correlation, the overall performance indicators of the all-in-one machine are decomposed into the performance indicators of each key module, so as to achieve the purpose of guiding and driving the performance tuning work of each key module, and can more accurately locate performance bottlenecks and provide more powerful support for performance optimization.

[0012] In one of the schemes, before obtaining the overall scope of the industrial simulation integrated machine to be evaluated, the method further includes: determining the overall scope of industrial software involved in the industrial simulation integrated machine to be evaluated; and performing testability verification on the overall scope.

[0013] In this plan, it is ensured that the evaluation method covers all key components and functions in the industrial simulation all-in-one machine, so as to ensure the comprehensiveness and accuracy of the evaluation. By determining the overall scope, it can be ensured that the evaluation results are representative and can fully reflect the performance status of the industrial simulation all-in-one machine, thereby improving the efficiency of the evaluation.

[0014] In one of the solutions, the key modules include at least server hardware, server operating system and industrial simulation software.

[0015] In one of the schemes, the update strategy is a first update strategy or a second update strategy; the first update strategy includes: according to the vertical stack relationship of the industrial simulation integrated machine to be evaluated, replacing the key module from bottom to top along the vertical stack to the benchmark whole; the second update strategy includes: according to the vertical stack relationship of the industrial simulation integrated machine to be evaluated, replacing the key module from top to bottom along the vertical stack to the benchmark whole.

[0016] In this solution, based on the specific situation of the overall performance, we can consider choosing a vertical update strategy from bottom to top or from top to bottom, which is convenient for selecting update strategies for different industrial simulation all-in-one machines, thereby shortening the evaluation time and improving the evaluation efficiency.

[0017] In one of the schemes, the updating of the benchmark entity through N key modules according to a preset update strategy includes: replacing the 1st key module to the N-1th key module of the benchmark entity according to the update strategy to obtain N-1 transition entities; replacing the Nth key module of the benchmark entity according to the update strategy to obtain the entity to be evaluated; and inserting the N-1 transition entities between the benchmark entity and the entity to be evaluated in a replacement order.

[0018] In this solution, the transition entity corresponding to the key modules is correlated with the entity to be evaluated, which can guide performance tuning from an overall perspective.

[0019] In one of the schemes, the performance tests are performed on the benchmark entity, N-1 transition entities, and the entity to be evaluated in sequence to obtain the test results of the entity to be evaluated and the N-1 transition entities, including:

[0020] Respectively obtain the solution time of the benchmark whole, N-1 transition wholes and the whole to be evaluated for the same simulation object;

[0021] Based on the comparison results between the benchmark entity and the entity to be evaluated, the performance score of the entity to be evaluated is calculated. , the calculation formula is as follows:

[0022]

[0023] Wherein, U is the performance score of the entity to be evaluated relative to the benchmark entity, For the overall performance of the benchmark, To evaluate the overall performance, is the overall solution time of the benchmark, The duration of solving the whole to be evaluated;

[0024] Respectively obtain the solution time of the reference whole and N-1 transition wholes for the same simulation object;

[0025] Based on the comparison results of the first transition whole and the benchmark whole, the performance score of the first key module is calculated, and the calculation formula is as follows:

[0026]

[0027] in, is the performance score of the first key module, For the overall performance of the benchmark, The overall performance of the transition described in the first paragraph is is the overall solution time for the benchmark, is the duration of solving the first transition as a whole;

[0028] Respectively obtain the solution time of the benchmark whole, N-1 transition wholes and the whole to be evaluated for the same simulation object;

[0029] Based on the comparison results of the N-2 transition as a whole and the N-1 transition as a whole, the performance score of the N-1 key module is calculated, and the calculation formula is as follows:

[0030]

[0031] in, is the performance score of the (N-1)th key module, is the performance of the N-1th transition ensemble, is the performance of the N-2th transition as a whole, is the duration of solving the N-1th transition as a whole, is the duration of solving the N-2 transition as a whole;

[0032] Based on the comparison results of the N-1th transition entity and the entity to be evaluated, the performance score of the Nth key module is calculated, and the calculation formula is as follows:

[0033]

[0034] in, is the performance score of the Nth key module, The overall performance for the Nth transition, is the performance of the N-1th transition ensemble, is the duration of solving the Nth transition as a whole, is the duration of solving the N-1th transition as a whole.

[0035] In one of the solutions, the method further includes: the test results of the entity to be evaluated and N-1 of the transition entities satisfy a verification formula, and the verification formula is as follows:

[0036]

[0037] Wherein, U is the performance score of the entity to be evaluated relative to the benchmark entity, is the performance score of the first key module obtained according to the preset decomposition method, Scoring the performance of key module 2… The performance score of the Nth key module.

[0038] In this solution, the performance score of the all-in-one machine is equal to being decomposed into several vertical dimensions. When the all-in-one machine includes the vertical dimensions of server hardware, server operating system, and solver software, the above three dimensions are used as three key modules. After constructing a transitional whole or an overall whole to be evaluated to obtain a corresponding performance score, the performance scores of the three key modules are multiplied to obtain a performance score that can represent the performance of the all-in-one machine.

[0039] In one of the schemes, an industrial simulation all-in-one machine performance evaluation device includes:

[0040] A data acquisition module, used to acquire the overall scope of the industrial simulation integrated machine to be evaluated;

[0041] An overall decomposition module, used for decomposing the overall scope into N key modules based on the vertical stack information of the industrial simulation integrated machine to be evaluated;

[0042] A performance tuning module matches a benchmark entity corresponding to the overall range, updates the benchmark entity through the N key modules with a preset update strategy, and obtains N-1 transition entities and 1 entity to be evaluated;

[0043] A performance testing module, used to perform performance tests on the benchmark entity, N-1 transition entities and the entity to be evaluated in sequence, and obtain test results of the entity to be evaluated and the N-1 transition entities;

[0044] A bottleneck location module, used to arrange the N key modules in ascending order based on the test results to obtain the bottleneck key module;

[0045] The report generation module is used to output an evaluation report based on the test results of the industrial simulation integrated machine to be evaluated, the test results of the N key modules and the bottleneck key module.

[0046] In this solution, the performance evaluation method of the industrial simulation all-in-one machine can be used to achieve vertical decomposition of the performance of the industrial simulation all-in-one machine, so that the overall performance of the all-in-one machine maintains a certain correlation with the performance of each key module on the vertical technology stack. Through this correlation, the overall performance indicators of the all-in-one machine are decomposed into the performance indicators of each key module, so as to achieve the purpose of guiding and driving the performance tuning work of each key module, and can more accurately locate performance bottlenecks and provide more powerful support for performance optimization.

[0047] In one of the schemes, a server includes a memory, one or more processors, and one or more applications; wherein the one or more applications are stored in the memory; when the one or more processors execute the one or more applications, the server implements the industrial simulation all-in-one machine performance evaluation method as described in any one of the above-mentioned schemes.

[0048] In one of the schemes, a computer program is stored in the storage medium, and the computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the industrial simulation all-in-one machine performance evaluation method as described in any one of the above-mentioned schemes. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0050] Figure 1 A schematic diagram showing a flow chart of a method for evaluating performance of an industrial simulation integrated machine according to an embodiment of the present invention;

[0051] Figure 2 A schematic diagram showing a process of obtaining an overall range according to an embodiment of the present invention;

[0052] Figure 3 A schematic diagram showing a process of updating the entire benchmark using a preset update strategy according to an embodiment of the present invention;

[0053] Figure 4 A schematic diagram showing the structure of an industrial simulation integrated machine performance evaluation device according to an embodiment of the present invention;

[0054] Figure 5 A schematic diagram showing a top-down optimization strategy according to an embodiment of the present invention, wherein a dotted rectangular box is a reference entity or a key module of the reference entity, and a solid rectangular box is a to-be-evaluated entity or a key module of the to-be-evaluated entity;

[0055] Figure 6 A schematic diagram showing a bottom-up optimization strategy according to an embodiment of the present invention, wherein a dotted rectangular box represents a benchmark entity or a key module of the benchmark entity, and a solid rectangular box represents an entity to be evaluated or a key module of the entity to be evaluated. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0058] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features limited to "first" and "second" may explicitly or implicitly include at least one of the features. In addition, if "and / or" or "and / or" appears in the full text, its meaning includes three parallel solutions. Taking "A and / or B" as an example, it includes solution A, solution B, or solutions that satisfy both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0059] Example 1

[0060] Please refer to Figure 1 One embodiment of the present invention provides a method for evaluating the performance of an industrial simulation integrated machine, comprising:

[0061] Step S100: obtaining the overall scope of the industrial simulation integrated machine to be evaluated, and decomposing the overall scope into N key modules based on the vertical stack information of the industrial simulation integrated machine to be evaluated;

[0062] Step S200, matching a reference entity corresponding to the overall range, and updating the reference entity by using the N key modules with a preset update strategy to obtain N-1 transition entities and 1 entity to be evaluated;

[0063] Step S300, sequentially performing performance tests on the benchmark entity, N-1 transition entities, and the entity to be evaluated, and obtaining test results of the entity to be evaluated and the N-1 transition entities;

[0064] Step S400: Arrange the N key modules in ascending order based on the test results to obtain bottleneck key modules;

[0065] Step S500: output an evaluation report based on the test results of the industrial simulation integrated machine to be evaluated, the test results of the N key modules, and the bottleneck key module.

[0066] In this embodiment, the performance evaluation method of the industrial simulation integrated machine can be used to realize the vertical decomposition of the performance of the industrial simulation integrated machine, so that the overall performance of the integrated machine maintains a certain correlation with the performance of each key module on the vertical technology stack. Through this correlation, the overall performance index of the integrated machine is decomposed into the performance index of each key module, so as to achieve the purpose of guiding and driving the performance tuning work of each key module, and can more accurately locate the performance bottleneck and provide more powerful support for performance optimization.

[0067] It can be understood that, in the embodiments of the present invention, the overall performance of the industrial all-in-one machine refers to the final solution performance of the industrial software currently used by the industrial all-in-one machine. The core of the present invention is how to find the key modules that can improve the solution performance of the industrial software, that is, to find the shortcoming in the all-in-one machine that has the greatest impact on the solution performance of the industrial software. The evaluation result obtained by evaluating the shortcoming of the overall performance of the all-in-one machine is more conducive to the optimization of the all-in-one machine; for example, when both the operating system and the processor running the industrial software have room for optimization, the evaluation method of this embodiment can obtain an evaluation result that the solution performance of the industrial software is mainly limited by the computing power of the processor. Based on this evaluation result, it is more conducive to the optimization of the all-in-one machine under the application of specific industrial software (such as explicit dynamics simulation software, general structural simulation software or electronic heat dissipation simulation software, etc.);

[0068] The present invention does not consider the performance evaluation of a single hardware in an industrial all-in-one machine alone. The optimization guided by the evaluation of a single hardware may be counterproductive and reduce the optimization speed. For example, blindly improving the hardware specifications of the all-in-one machine, such as network interface performance, device heat dissipation capacity, or simple processor computing power, will only have a negligible or even no improvement in the solution performance of the industrial software.

[0069] Please refer to Figure 2 In one embodiment, before obtaining the overall scope of the industrial simulation integrated machine to be evaluated, the method further includes:

[0070] Step S120, determining the overall scope of the industrial software in the industrial simulation all-in-one machine to be evaluated;

[0071] Step S110: performing testability verification on the entire range.

[0072] In this embodiment, it is ensured that the evaluation method covers all key components and functions in the industrial simulation all-in-one machine, thereby ensuring the comprehensiveness and accuracy of the evaluation, and by determining the overall scope, it can be ensured that the evaluation results are representative and can fully reflect the performance status of the industrial simulation all-in-one machine.

[0073] By conducting measurability verification, we can ensure that the evaluation method is operational and reliable, the accuracy and credibility of the evaluation results are guaranteed, and reduce the situation where it is found that the necessary data cannot be obtained during the evaluation process and the evaluation scope needs to be reselected, thereby improving the efficiency of the evaluation.

[0074] In one embodiment, the key modules include at least server hardware, server operating system and industrial simulation software.

[0075] In this embodiment, by evaluating the performance of the server hardware and timely optimizing the server hardware with poor performance, higher computing performance and stability can be provided, thereby accelerating the industrial simulation process, improving simulation accuracy and efficiency, and improving the continuity and stability of industrial production. By evaluating the performance of the server operating system, timely upgrading a stable and efficient server operating system can provide good system stability and performance, and ensure the smooth and reliable operation of the industrial simulation system. By evaluating the adaptability of the industrial simulation software in the current industrial simulation all-in-one machine, timely adjusting the adaptability settings of the industrial simulation software, reducing the user's learning cost, and then helping users optimize the production process, improve production efficiency, and reduce costs, thereby enhancing the overall competitiveness of industrial production; or predicting potential problems and risks in the production process, taking corresponding measures to optimize and improve, and avoiding unnecessary losses and waste in production.

[0076] In one of the embodiments, the update strategy is a first update strategy or a second update strategy;

[0077] Please refer to Figure 5 , the first update strategy includes: according to the vertical stack relationship of the industrial simulation integrated machine to be evaluated, replacing the key module from bottom to top along the vertical stack to the benchmark whole; wherein, As the benchmark, is the first transition entity, is the entity to be evaluated; It is the performance score of the first key module obtained according to the established decomposition method (such as bottom-up). is the performance score of the second key module, and so on. is the Nth key performance score.

[0078] Please refer to Figure 6The second update strategy includes: according to the vertical stack relationship of the industrial simulation integrated machine to be evaluated, replacing the key module from top to bottom along the vertical stack to the benchmark whole; wherein, As the benchmark, is the first transition entity, is the entity to be evaluated; It is the performance score of the first key module obtained according to the established decomposition method (such as top-down). is the performance score of the second key module, and so on. is the Nth key performance score.

[0079] In this embodiment, based on the specific situation of the overall performance, it is possible to consider selecting a vertical update strategy from bottom to top or from top to bottom, which is convenient for selecting update strategies for different industrial simulation all-in-one machines, thereby shortening the evaluation time and improving the evaluation efficiency.

[0080] Please refer to Figure 3 In one embodiment, the updating of the benchmark as a whole by using the N key modules with a preset update strategy includes:

[0081] Step S210: replacing the 1st key module to the N-1th key module of the reference whole according to the update strategy to obtain N-1 transitional wholes;

[0082] Step S220: replacing the Nth key module of the benchmark entity according to the update strategy to obtain the entity to be evaluated;

[0083] Step S230: insert N-1 transitional entities between the reference entity and the entity to be evaluated in a replacement order.

[0084] In this embodiment, by replacing the 1st key module to the Nth key module of the benchmark whole according to the update strategy, N-1 transition wholes and wholes to be evaluated are obtained; any two key modules therein are correlated when comparing performance, avoiding large errors in results between different key modules, which makes it impossible to locate specific bottlenecks; and, the transition whole corresponding to the key modules is correlated with the whole to be evaluated, which can guide performance tuning from an overall perspective.

[0085] In one embodiment, the performance test is performed on the benchmark entity, N-1 transition entities and the entity to be evaluated in sequence to obtain the test results of the entity to be evaluated and the N-1 transition entities, including:

[0086] Respectively obtain the solution time of the benchmark whole, N-1 transition wholes and the whole to be evaluated for the same simulation object;

[0087] Based on the comparison results between the benchmark entity and the entity to be evaluated, the performance score U of the entity to be evaluated is calculated using the following formula:

[0088]

[0089] Wherein, U is the performance score of the entity to be evaluated relative to the benchmark entity, For the overall performance of the benchmark, To evaluate the overall performance, is the overall solution time of the benchmark, The duration of solving the whole to be evaluated;

[0090] Respectively obtain the solution time of the reference whole and N-1 transition wholes for the same simulation object;

[0091] Based on the comparison results of the first transition whole and the benchmark whole, the performance score of the first key module is calculated, and the calculation formula is as follows:

[0092]

[0093] in, is the performance score of the first key module, For the overall performance of the benchmark, The overall performance of the transition described in the first paragraph is is the overall solution time for the benchmark, is the duration of the solution of the first transition as a whole; P stands for Performance; T stands for the duration of the solution. Performance and duration of the solution are inversely proportional to each other, that is, performance is equal to the inverse of the duration of the solution, that is:

[0094] ,so .

[0095] Respectively obtain the solution time of the benchmark whole, N-1 transition wholes and the whole to be evaluated for the same simulation object;

[0096] Based on the comparison results of the N-2 transition as a whole and the N-1 transition as a whole, the performance score of the N-1 key module is calculated, and the calculation formula is as follows:

[0097]

[0098] in, is the performance score of the (N-1)th key module, is the performance of the N-1th transition ensemble, is the performance of the N-2th transition as a whole, is the duration of solving the N-1th transition as a whole, is the duration of solving the N-2 transition as a whole;

[0099] Based on the comparison results of the N-1th transition entity and the entity to be evaluated, the performance score of the Nth key module is calculated, and the calculation formula is as follows:

[0100]

[0101] in, is the performance score of the Nth key module, The overall performance for the Nth transition, The overall performance of the N-1th transition is the duration of solving the Nth transition as a whole, is the duration of solving the N-1th transition as a whole.

[0102] In this embodiment, the solution time of the benchmark whole can be directly obtained by the calculation formula of the performance score of the whole to be evaluated. and the overall solution time to be evaluated , and the overall performance of the industrial simulation all-in-one machine is calculated.

[0103] Furthermore, the solution time of the N-1th transition as a whole can be directly obtained by using the calculation formula of the performance score of the Nth key module. and the solution time of the N-2 transition as a whole , calculate the performance score of the Nth key module of the industrial simulation all-in-one machine .

[0104] In one embodiment, the method further includes: the test results of the entity to be evaluated and N-1 transition entities satisfy a verification formula, and the verification formula is as follows:

[0105]

[0106] Wherein, U is the performance score of the entity to be evaluated relative to the benchmark entity, is the performance score of the first key module obtained according to the preset decomposition method, Scoring the performance of key module 2… The performance score of the Nth key module.

[0107] In this embodiment, the performance score of the all-in-one machine is equal to being decomposed into several vertical dimensions. When the all-in-one machine includes the vertical dimensions of server hardware, server operating system and solver software, the above three dimensions are used as three key modules. After constructing a transitional whole or an overall whole to be evaluated to obtain a corresponding performance score, the performance scores of the three key modules are multiplied to obtain a performance score that can represent the performance of the all-in-one machine.

[0108] In an application scenario of this embodiment, by verifying the test results, errors in the performance scoring results between key modules are avoided, which results in the inability to locate specific bottlenecks.

[0109] Please refer to Figure 4 In one embodiment, a performance evaluation device for an industrial simulation all-in-one machine includes:

[0110] The data acquisition module 100 is used to acquire the overall scope of the industrial simulation integrated machine to be evaluated;

[0111] An overall decomposition module 200, configured to decompose the overall scope into N key modules based on the vertical stack information of the industrial simulation integrated machine to be evaluated;

[0112] The whole replacement module 300 matches the reference whole corresponding to the whole range, updates the reference whole by using the N key modules with a preset update strategy, and obtains N-1 transitional wholes and 1 whole to be evaluated;

[0113] The performance testing module 400 is used to perform performance tests on the benchmark entity, N-1 transition entities and the entity to be evaluated in sequence, and obtain test results of the entity to be evaluated and the N-1 transition entities;

[0114] A bottleneck location module 500 is used to arrange the N key modules in ascending order based on the test results to obtain a bottleneck key module;

[0115] The report generation module 600 is used to output an evaluation report based on the test results of the industrial simulation integrated machine to be evaluated, the test results of the N key modules and the bottleneck key module.

[0116] In this embodiment, the performance evaluation method of the industrial simulation integrated machine can be used to realize the vertical decomposition of the performance of the industrial simulation integrated machine, so that the overall performance of the integrated machine maintains a certain correlation with the performance of each key module on the vertical technology stack. Through this correlation, the overall performance index of the integrated machine is decomposed into the performance index of each key module, so as to achieve the purpose of guiding and driving the performance tuning work of each key module, and can more accurately locate the performance bottleneck and provide more powerful support for performance optimization.

[0117] In one of the embodiments, a server includes a memory, one or more processors, and one or more applications; wherein the one or more applications are stored in the memory; when the one or more processors execute the one or more applications, the server implements the industrial simulation all-in-one machine performance evaluation method as described in any one of the above-mentioned embodiments.

[0118] In one of the embodiments, a computer program is stored in the storage medium, and the computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the industrial simulation all-in-one machine performance evaluation method as described in any one of the above-mentioned embodiments.

[0119] Example 2

[0120] This embodiment provides an industrial simulation integrated machine optimization method, including:

[0121] Step B100: iterating the industrial simulation integrated machine to be optimized based on the evaluation report, and performing performance evaluation on the iterated industrial simulation integrated machine, wherein the evaluation report is obtained based on the evaluation method of Example 1;

[0122] Step B200: Based on the evaluation report of the industrial simulation integrated machine to be optimized and the evaluation report of the industrial simulation integrated machine after iteration, the performance scores of the key modules in the industrial simulation integrated machine before and after iteration are compared, and the key module comparison results are output;

[0123] Step B300: Based on the comparison result of the key modules, determine whether the bottleneck key module of the iterative industrial simulation integrated machine is the same as the bottleneck key module of the industrial simulation integrated machine to be optimized; if the bottleneck key modules are different, output the bottleneck key module of the iterative industrial simulation integrated machine as the performance bottleneck; if the bottleneck key modules are the same, output the bottleneck key module of the industrial simulation integrated machine before optimization as the performance bottleneck;

[0124] Step B400: Based on the evaluation report of the industrial simulation integrated machine to be optimized and the evaluation report of the industrial simulation integrated machine after iteration, the overall performance of the industrial simulation integrated machine before and after iteration is compared, and the overall performance comparison result is output;

[0125] Step B500: judging whether the iteration of the industrial simulation integrated machine after iteration is successful based on the overall performance comparison result; if the iteration is successful, outputting an evaluation report of the industrial simulation integrated machine after iteration; if the iteration fails, repeating the iteration process of step B100 to step B500;

[0126] Step B600: Based on the evaluation report of the iterated industrial simulation integrated machine, determine whether the overall performance of the iterative industrial simulation integrated machine meets the expected target performance; if it meets the expected target performance, output the iterative industrial simulation integrated machine as an optimized industrial simulation integrated machine; if it does not meet the expected target performance, repeat the iterative process of step B100-step B500.

[0127] In this embodiment, the industrial simulation integrated machine is iterated by optimizing the performance bottleneck, and the industrial simulation integrated machine of each iteration is evaluated by the evaluation method of embodiment 1 to obtain the new performance scores of the N key modules of the corresponding iteration round. , ,...and ; By comparing the new , ,...and Compared with the old one in the previous iteration , ,...and ; Determine whether the performance bottleneck that most affects the overall performance has changed. If so, focus the next round of performance tuning on the key modules represented by the new performance bottleneck;

[0128] And, by verifying the formula , the overall performance of the industrial simulation integrated machine in this iteration can be calculated. If the overall performance of this iteration is improved compared with the previous iteration, it can be proved that this iteration is successful. The overall performance of the industrial simulation integrated machine in this iteration is compared with the expected target performance until the expected target performance is reached, and the tuning work is completed.

[0129] It can be understood that in this embodiment, the vertical decomposition of the performance of the industrial simulation all-in-one machine is based on the correlation between the overall performance of the all-in-one machine and the performance of each key module on the vertical technology stack. In the optimization process, the performance evaluation report obtained based on this correlation can more specifically locate the specific bottleneck of the all-in-one machine, guide performance tuning from an overall perspective, improve the efficiency of the iteration of the industrial simulation all-in-one machine, and obtain an industrial simulation all-in-one machine that meets the expected target performance more quickly.

[0130] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or directly / indirectly applied in other related technical fields are included in the patent protection scope of the present invention.

Claims

1. A performance evaluation method for an industrial simulation integrated machine, characterized in that: include: Obtaining the overall scope of the industrial simulation integrated machine to be evaluated, and decomposing the overall scope into N key modules based on the vertical stack information of the industrial simulation integrated machine to be evaluated; Matching a reference whole corresponding to the whole range, updating the reference whole by using the N key modules with a preset update strategy, and obtaining (N-1) transitional wholes and 1 whole to be evaluated; Performing performance tests on the benchmark entity, (N-1) transition entities, and the entity to be evaluated in sequence to obtain test results of the entity to be evaluated and the (N-1) transition entities; Arrange the N key modules in ascending order based on the test results to obtain the bottleneck key module; Based on the test results of the industrial simulation integrated machine to be evaluated, the test results of the N key modules and the bottleneck key module, an evaluation report is output.

2. The industrial simulation integrated machine performance evaluation method according to claim 1, characterized in that: Before obtaining the overall scope of the industrial simulation integrated machine to be evaluated, the method further includes: Determine the overall scope of industrial software involved in the industrial simulation all-in-one machine to be evaluated; The entire scope is subjected to testability verification.

3. The industrial simulation integrated machine performance evaluation method according to claim 1, characterized in that: The key modules include at least server hardware, server operating system and industrial simulation software.

4. The performance evaluation method of an industrial simulation integrated machine according to any one of claims 1 to 3, characterized in that: The update strategy is the first update strategy or the second update strategy; The first update strategy includes: according to the vertical stack relationship of the industrial simulation integrated machine to be evaluated, replacing the key module from bottom to top along the vertical stack to the benchmark whole; The second update strategy includes: according to the vertical stack relationship of the industrial simulation integrated machine to be evaluated, replacing the key module from top to bottom along the vertical stack to the benchmark whole.

5. The industrial simulation integrated machine performance evaluation method according to claim 4, characterized in that: The updating of the benchmark as a whole by using the N key modules with a preset updating strategy includes: According to the update strategy, the first key module to the (N-1)th key module of the reference whole are replaced to obtain (N-1) transitional wholes; Replace the Nth key module of the benchmark entity according to the update strategy to obtain the entity to be evaluated; Insert (N-1) transitional entities between the reference entity and the entity to be evaluated in a replacement order.

6. The industrial simulation integrated machine performance evaluation method according to claim 1, characterized in that: The step of sequentially performing performance tests on the benchmark entity, the (N-1) transition entities, and the entity to be evaluated to obtain test results of the entity to be evaluated and the (N-1) transition entities includes: Respectively obtain the solution time of the benchmark whole, (N-1) transition wholes and the whole to be evaluated for the same simulation object; Based on the comparison results between the benchmark entity and the entity to be evaluated, the performance score U of the entity to be evaluated is calculated using the following formula: in, is the performance score of the entity to be evaluated relative to the benchmark entity, For the overall performance of the benchmark, To evaluate the overall performance, is the overall solution time of the benchmark, The duration of solving the whole to be evaluated; Alternatively, based on the comparison result of the first transition whole and the benchmark whole, the performance score of the first key module is calculated, and the calculation formula is as follows: in, is the performance score of the first key module, For the overall performance of the benchmark, The overall performance of the transition described in the first paragraph is is the overall solution time for the benchmark, is the duration of solving the first transition as a whole; Alternatively, based on the comparison result of the (N-1)th transition entity and the entity to be evaluated, the performance score of the Nth key module is calculated, and the calculation formula is as follows: in, is the performance score of the Nth key module, The overall performance for the Nth transition, is the performance of the (N-1)th transition ensemble, is the duration of solving the Nth transition as a whole, is the duration of solving the (N-1)th transition as a whole.

7. The performance evaluation method of the industrial simulation integrated machine according to claim 6, characterized in that: The test results of the entity to be evaluated and (N-1) transition entities satisfy the verification formula, which is as follows: Wherein, U is the performance score of the entity to be evaluated relative to the benchmark entity, is the performance score of the first key module obtained according to the preset decomposition method, Scoring the performance of key module 2… is the performance score of the Nth key module.

8. An industrial simulation integrated machine performance evaluation device, characterized in that: The device at least comprises: A data acquisition module, used to acquire the overall scope of the industrial simulation integrated machine to be evaluated; An overall decomposition module, used for decomposing the overall scope into N key modules based on the vertical stack information of the industrial simulation integrated machine to be evaluated; A performance tuning module matches a benchmark entity corresponding to the overall range, updates the benchmark entity with a preset update strategy through the N key modules, and obtains (N-1) transition entities and 1 entity to be evaluated; A performance testing module, used to perform performance tests on the benchmark entity, (N-1) transition entities and the entity to be evaluated in sequence, and obtain test results of the entity to be evaluated and the (N-1) transition entities; A bottleneck location module, used for arranging the N key modules in ascending order based on the test results to obtain the bottleneck key module; The report generation module is used to output an evaluation report based on the test results of the industrial simulation integrated machine to be evaluated, the test results of the N key modules and the bottleneck key module.

9. A server, characterized in that: The server includes a memory, one or more processors and one or more applications; wherein the one or more applications are stored in the memory; when the one or more processors execute the one or more applications, the server implements the industrial simulation all-in-one machine performance evaluation method as described in any one of claims 1-7.

10. A storage medium, characterized in that: The storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the industrial simulation all-in-one machine performance evaluation method as described in any one of claims 1 to 7.

Images