Adaptation evaluation method of application software in domestic CPU hardware, equipment and medium

Abstract

The invention discloses an adaptation method and device of application software in domestic CPU hardware and a medium, and the evaluation method comprises the following steps: S1, calculating an adaptation instruction set compatibility index of the application software in bottom-layer domestic CPU hardware, S2, calculating an adaptation performance evaluation index of the application software in the bottom-layer domestic CPU hardware, the method comprises the steps of S1, calculating application software in bottom layer domestic CPU hardware, S2, calculating adaptation stability indexes of the application software in the bottom layer domestic CPU hardware, S4, determining specific weights of the indexes on the basis of an analytic hierarchy process, S5, evaluating an adaptation score of the application software in the bottom layer domestic CPU hardware, and S6, programming the steps and outputting a monitoring result in real time. According to the method, a simulation test and actual operation combined mode is adopted, the adapted application software is comprehensively evaluated, the adaptation work of the application software on domestic CPU hardware can be effectively guided, the adaptation effect is accurately measured, and potential problems are found.

Description

Technical Field

[0001] The present invention relates to the field of software adaptation, and in particular to a method, device and medium for evaluating the adaptation of application software in domestic CPU hardware. Background Art

[0002] In recent years, with the profound changes in the international situation and the increasingly fierce competition in the information technology industry, independent control of core technologies has become a key strategic direction for the development of my country's information technology industry. As the core hardware foundation of the information industry, the performance improvement and ecological improvement of domestic CPUs play an irreplaceable role in ensuring national information security and promoting high-quality development of the digital economy. From Loongson's exploration of independent instruction set architecture, to Feiteng's innovative breakthroughs based on ARM architecture, to Zhaoxin's localization practice of X86 architecture, domestic CPUs have made continuous progress in performance, power consumption and other aspects, gradually breaking the foreign monopoly. However, the advantages of hardware performance need to be well adapted and coordinated with application software to fully release the computing power potential and build a complete domestic information technology ecosystem.

[0003] The adaptation process of application software and underlying domestic CPU hardware faces many challenges. Unlike the mature international mainstream CPU ecosystem, there are large differences in the instruction set architecture and micro-architecture design of domestic CPUs. This makes it difficult for a large number of traditional application software developed based on foreign CPUs to run efficiently directly on domestic CPUs. Taking office software as an example, compatibility issues may arise in the domestic CPU environment, such as missing functions, running lags, and even inability to start, which greatly affects the user experience. At the same time, the uniqueness of domestic CPU hardware in instruction execution efficiency, cache management mechanism, etc. requires application software to be targeted optimized and adjusted to maximize performance. In addition, different domestic CPU manufacturers have different focuses on architectural design and technical routes, further increasing the complexity and diversity of application software adaptation.

[0004] Scientific and comprehensive evaluation of the adaptation effect of application software in the underlying domestic CPU hardware is a key link in ensuring adaptation quality and promoting the development of the domestic CPU ecosystem. Adaptation evaluation can not only objectively measure the operating performance, stability and compatibility of application software on the domestic CPU platform, but also provide data support for subsequent optimization and improvement. Through evaluation, performance bottlenecks in the adaptation process can be discovered, such as slow processing speed of compute-intensive tasks, excessive memory usage, low efficiency of multi-threaded collaboration, etc., and then guide developers to carry out targeted code optimization and function adjustments. In addition, a reasonable evaluation system can also provide market feedback for domestic CPU hardware manufacturers, help them clarify the direction of product technology improvement, and promote collaborative innovation of hardware and software.

[0005] At present, in the field of adaptation and evaluation of application software and domestic CPU hardware, although there have been certain research and practical explorations, there are still many shortcomings. The adaptation process lacks unified technical specifications and standard processes, resulting in low adaptation efficiency and uneven adaptation results; the evaluation system is not perfect, and the selection of evaluation indicators lacks systematicity and scientificity, making it difficult to fully reflect the true performance of application software on domestic CPU platforms. Therefore, in-depth research on the adaptation and evaluation of application software in the underlying domestic CPU hardware and the exploration of a set of scientific, efficient and operational adaptation and evaluation methods have important theoretical value and practical significance for promoting the development of the domestic CPU industry and improving the domestic information technology ecosystem. Summary of the Invention

[0006] In order to overcome the above problems, the purpose of the present invention is to provide an adaptation evaluation method, device and medium for application software in domestic CPU hardware to solve the problems raised in the above background technology.

[0007] The technical solution adopted in the present invention is:

[0008] The adaptation evaluation method of application software in domestic CPU hardware includes the following steps:

[0009] S1: Computes the instruction set compatibility indicators of the application software in the underlying domestic CPU hardware, including instruction coverage and instruction execution efficiency difference rate;

[0010] S2: Computes the performance evaluation indicators of application software in the underlying domestic CPU hardware, including running speed and resource utilization;

[0011] S3: Computes the adaptability stability indicators of application software in the underlying domestic CPU hardware, including failure rate and recovery time;

[0012] S4: Determine the specific weights of the above indicators based on the analytic hierarchy process (AHP);

[0013] S5: Evaluates the adaptability score of the application software in the underlying domestic CPU hardware;

[0014] S6: Program the above steps and output the monitoring results in real time.

[0015] As a further description of the present invention, the calculation formula for the instruction coverage in S1 is:

[0016] ,

[0017] in, A set of application software instructions. Represents the first instructions, is the total number of application software instructions,

[0018] For the domestic CPU instruction set, Indicates the first instruction in the domestic CPU instruction set instructions, is the total number of instructions in the domestic CPU instruction set,

[0019] is an indicator function and satisfies, when hour ,otherwise , which are instructions in application software When it exists in the domestic CPU instruction set C, If it does not exist, then ,

[0020] is the instruction importance weight coefficient,

[0021] The calculation formula for the instruction execution efficiency difference rate in S1 is:

[0022] ,

[0023] in,

[0024] Is the instruction execution frequency, that is, the number of times an instruction is executed within a certain period of time,

[0025] Is the standard reference CPU The execution frequency of an instruction, that is, the number of times the instruction is executed within a certain period of time;

[0026] Is the standard reference CPU The execution time of the instructions;

[0027] It is the first domestically produced CPU The execution frequency of the instructions;

[0028] It is the first domestically produced CPU The execution time of the instructions;

[0029] : Weighted instruction execution efficiency difference rate.

[0030] As a further description of the present invention, the calculation formula of the running speed in S2 is:

[0031] ,

[0032] in, Represents the task weight, which is used to reflect the importance of different tasks to software performance evaluation. The value is between 0 and 1, and the sum of all task weights is 1;

[0033] Indicates the total number of tasks;

[0034] Indicates the The speed at which tasks are run;

[0035] Represents the comprehensive running speed evaluation of multiple tasks, taking into account the running speed and weight of different tasks;

[0036] The resource utilization in S2 includes CPU utilization, memory utilization, and storage utilization.

[0037] The calculation formula of the CPU utilization is:

[0038] ,

[0039] in, Indicates the final CPU utilization evaluation index, taking into account CPU utilization and load balancing.

[0040] Indicates CPU utilization, which measures how busy the CPU is during the time interval.

[0041] Indicates the CPU load balancing coefficient, which is used to evaluate the load balancing of each CPU core. The closer the value is to 1, the more balanced the load is.

[0042] The calculation formula of the memory utilization is:

[0043] Define the total system memory size as , the memory size used by the application software is , memory utilization for:

[0044] ,

[0045] Consider memory fragmentation rate , that is, the impact of the ratio of memory fragment size to total memory on the effective use of memory. The improved memory utilization is expressed as,

[0046] ,

[0047] The calculation formula of the storage utilization is:

[0048] Define the total storage capacity as , the used storage capacity is , storage utilization for:

[0049] ,

[0050] Considering the impact of storage read and write speed on software performance, let the average storage read and write speed be , standard read and write speed is , introducing storage performance correction factor ,The final storage utilization evaluation index is expressed as,

[0051]

[0052] in, Indicates the total storage capacity; Indicates the used storage capacity; Indicates storage utilization, which measures storage resource usage; Indicates the average storage read and write speed; Indicates standard read and write speed; Indicates the storage performance correction factor, reflecting the impact of storage read and write speed on software performance; This is the final storage utilization evaluation indicator, which comprehensively considers the impact of storage utilization and read and write speed.

[0053] As a further description of the present invention, the calculation formula of the failure rate in S3 is:

[0054] ,

[0055] in, Indicates the fault severity coefficient, which is used to reflect the difference in the impact of different faults on software use. The value ranges from 0 to 1. The more serious the fault, the higher the The bigger;

[0056] FR' represents the failure rate, taking into account the failure severity coefficient;

[0057] Indicates the application software in the time interval The number of failures that occurred within

[0058] The calculation formula for the recovery time in S3 is:

[0059] ,

[0060] in, The user impact coefficient is determined based on the degree of loss to users caused by software unavailability during fault recovery, and its value ranges from 0 to 1.

[0061] It represents the final recovery time evaluation indicator, which takes into account the average recovery time and user impact;

[0062] The mean recovery time is calculated by adding up the recovery time of each fault and taking the average:

[0063] ,

[0064] is the recovery time of the jth failure of the application software,

[0065] Indicates that there are two or more occurrences in the statistical interval. Secondary failure.

[0066] As a further description of the present invention, the specific steps of S4 are:

[0067] Step 1: Construct a judgment matrix.

[0068] The definition criteria layer has indicators, namely , construct the judgment matrix ,in Indicator Relative to the indicator The importance of meeting Taking the three criteria-level indicators of instruction set compatibility, performance evaluation, and stability evaluation as examples, five experts were invited to score the importance of the indicators, and the average value was taken to obtain the judgment matrix A;

[0069] Step 2: Calculate the weight vector using the sum-product method;

[0070] Step 3: consistency test, by calculating the consistency index CI and consistency ratio CR, to determine whether the judgment matrix has satisfactory consistency. When , the consistency of the judgment matrix is ​​considered acceptable and the weight vector is valid.

[0071] As a further description of the present invention, the calculation formula for the adaptability score in S5 is:

[0072] ,

[0073] in, Indicates the adaptability score of the application software in the underlying domestic CPU hardware.

[0074] Indicates the Technical indicators,

[0075] Indicates the The weight corresponding to each indicator.

[0076] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for evaluating the adaptation of the application software in domestic CPU hardware is implemented.

[0077] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the adaptation evaluation method of the application software in domestic CPU hardware.

[0078] The beneficial effects of the present invention are:

[0079] The adaptation evaluation method of application software in domestic CPU hardware of the present invention constructs a multi-dimensional evaluation system including performance indicators, functional integrity, stability and compatibility, and adopts a combination of simulation testing and actual operation to comprehensively evaluate the adapted application software. Experimental verification shows that this research method can effectively guide the adaptation work of application software on domestic CPU hardware, accurately measure the adaptation effect, and discover potential problems. It provides a scientific solution and practical reference for improving the quality and performance of application software in the domestic CPU hardware ecosystem, and is of great significance for promoting the widespread application and industrial development of domestic CPU hardware. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Figure 1 This is a flow chart of the adaptation evaluation method for application software in domestic CPU hardware proposed by the present invention;

[0081] Figure 2 This is a case analysis and test result diagram of the adaptation evaluation method of the application software proposed in this invention in domestic CPU hardware. DETAILED DESCRIPTION

[0082] The specific implementation of the present invention is described below with reference to the accompanying drawings and embodiments:

[0083] It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the conditions under which the present invention can be implemented. Any structural modification, change in proportional relationship or adjustment of size should still fall within the scope of the technical content disclosed in the present invention without affecting the efficacy and purpose that can be achieved by the present invention.

[0084] At the same time, the terms such as "upper", "lower", "left", "right", "middle" and "one" quoted in this specification are only for the convenience of description and are not used to limit the scope of implementation of the present invention. Changes or adjustments to their relative relationships should be regarded as the scope of implementation of the present invention without substantially changing the technical content.

[0085] like Figures 1-2 As shown, it shows a specific embodiment of the present invention:

[0086] Example 1

[0087] In this embodiment, Figure 1 As shown, the adaptation evaluation method of application software in domestic CPU hardware is characterized by comprising the following steps:

[0088] S1: Computational application software's instruction set compatibility index in the underlying domestic CPU hardware;

[0089] S2: Computes the performance evaluation index of application software in the underlying domestic CPU hardware;

[0090] S3: Computes the adaptability stability index of application software in the underlying domestic CPU hardware;

[0091] S4: Determine the specific weights of the above indicators based on the analytic hierarchy process (AHP);

[0092] S5: Evaluates the adaptability score of the application software in the underlying domestic CPU hardware;

[0093] S6: Program the above steps and output the monitoring results in real time.

[0094] Furthermore, the following steps are included to calculate the application software's instruction set compatibility index in the underlying domestic CPU hardware:

[0095] The application software's instruction set compatibility indicators for the underlying domestic CPU hardware include: instruction coverage and instruction execution efficiency difference rate;

[0096] Define the application software instruction set as , the domestic CPU instruction set is ; Define indicator function Satisfied, when hour ;otherwise ; Then the mathematical formula of instruction coverage IC is:

[0097] ,

[0098] in, Represents a set of application software instructions, where Represents the first instructions, is the total number of application software instructions; Represents the domestic CPU instruction set, Indicates the first instruction in the domestic CPU instruction set instructions, is the total number of instructions in the domestic CPU instruction set; To indicate the function, when the instruction in the application software Exists in domestic CPU instruction sets China Times, If it does not exist, then , used to determine whether instructions are compatible; IC, or instruction coverage, is an indicator to measure the compatibility between application software instructions and domestic CPU instruction sets. It is obtained by calculating the proportion of application software instructions covered by domestic CPU instruction sets to the total number of application software instructions.

[0099] Considering that different instructions may have different importance in software operation, the instruction importance weight coefficient is introduced , improved instruction coverage The formula is:

[0100] ,

[0101] in, Indicates the instruction importance weight coefficient, which is used to reflect the importance of different instructions in software operation. The value range is between 0 and 1, and the sum of the weight coefficients of all instructions is 1; It represents the improved instruction coverage. The instruction importance weight coefficient is taken into account in the calculation, which can more accurately reflect the actual impact of instruction set compatibility on software adaptation. The core computing instructions can be given a higher weight, while the auxiliary instructions have a relatively lower weight, so as to more accurately reflect the actual impact of instruction set compatibility on software adaptation.

[0102] For the instruction execution efficiency difference rate, the average execution time of the application software executing the instruction set on the standard reference CPU is defined as , the average execution time of executing the same instruction set on a domestic CPU is , instruction execution efficiency difference rate The calculation formula is:

[0103] ,

[0104] in, It is the average execution time of the application software to execute the instruction set on a standard reference CPU, used as a comparison benchmark; It is the average execution time of application software executing the same instruction set on domestic CPUs; It is the instruction execution efficiency difference rate, which reflects the difference between the efficiency of domestic CPUs in executing application software instructions and the standard reference CPU;

[0105] To more comprehensively measure the efficiency of instruction execution, consider the frequency of instruction execution (the number of times a certain instruction is executed within a certain period of time), introducing the weighted instruction execution efficiency difference rate :

[0106] ,

[0107] in, is the execution frequency of the ith instruction on the standard reference CPU, that is, the number of times the instruction is executed within a certain period of time; is the execution time of the ith instruction on the standard reference CPU; is the execution frequency of the ith instruction on the domestic CPU; is the execution time of the ith instruction on the domestic CPU; : Weighted instruction execution efficiency difference rate, which comprehensively considers instruction execution frequency and execution time to measure instruction execution efficiency more comprehensively.

[0108] Furthermore, the following steps are included to calculate the adaptation performance evaluation index of the application software in the underlying domestic CPU hardware:

[0109] The performance evaluation indicators of application software’s adaptation to the underlying domestic CPU hardware include: running speed and resource utilization;

[0110] For running speed, the set of operation steps for the application software to complete a specific task is defined as , the execution time of each operation step on the domestic CPU is , then the total time to complete the task is expressed as,

[0111] ,

[0112] in, It represents a set of operation steps for application software to complete a specific task. It is one of the Operation steps, is the total number of operation steps; Indicates that the application software is executed on the domestic CPU The time for each operation step, It represents the total time for application software to complete a specific task on a domestic CPU, obtained by adding up the execution time of each operation step;

[0113] The running speed index RS is defined as the inverse of the total task time and is expressed as:

[0114] ,

[0115] in, It represents the running speed index, which is the inverse of the total task time and is used to measure how fast the software completes the task on the domestic CPU;

[0116] Since different tasks have different importance to software performance evaluation, task weights are introduced. , comprehensive running speed evaluation for multiple tasks for:

[0117] ,

[0118] in, Represents the task weight, which is used to reflect the importance of different tasks to software performance evaluation. The value is between 0 and 1, and the sum of all task weights is 1; Indicates the total number of tasks; Indicates the The speed at which tasks are run; Represents the comprehensive running speed evaluation of multiple tasks, taking into account the running speed and weight of different tasks;

[0119] Furthermore, the following steps are included to calculate the resource utilization of the application software adapted to the underlying domestic CPU hardware:

[0120] Resource utilization includes: CPU utilization, memory utilization, and storage utilization;

[0121] For CPU utilization, define the time interval in which the application software The time that the CPU is busy is , then the CPU utilization for:

[0122] ,

[0123] in, Indicates the length of the statistical time interval; Indicates the application software in the time interval The time during which the CPU is busy; Indicates CPU utilization, which measures how busy the CPU is during the time interval;

[0124] Considering the load balancing of different CPU cores, the number of cores is defined as , No. cores in the time interval The busy time in , introduce CPU load balancing coefficient :

[0125] ,

[0126] in, Indicates the number of CPU cores; Indicates the cores in the time interval Busy time within Indicates the CPU load balancing coefficient, which is used to evaluate the load balancing of each CPU core. The closer the value is to 1, the more balanced the load.

[0127] Finally, the CPU utilization evaluation index can be expressed as,

[0128] ,

[0129] in, Indicates the final CPU utilization evaluation indicator, which comprehensively considers CPU utilization and load balancing.

[0130] For memory utilization, define the total system memory size as , the memory size used by the application software is , memory utilization for:

[0131] ,

[0132] Consider memory fragmentation rate The impact of (the ratio of memory fragment size to total memory) on the effective use of memory, the improved memory utilization is expressed as,

[0133] ,

[0134] For storage utilization, define the total storage capacity as , the used storage capacity is , storage utilization for:

[0135] ,

[0136] Considering the impact of storage read and write speed on software performance, let the average storage read and write speed be , standard read and write speed is , introducing storage performance correction factor ,The final storage utilization evaluation index is expressed as,

[0137] ,

[0138] in, Indicates the total storage capacity; Indicates the used storage capacity; Indicates storage utilization, which measures storage resource usage; Indicates the average storage read and write speed; Indicates standard read and write speed; Indicates the storage performance correction factor, reflecting the impact of storage read and write speed on software performance; This represents the final storage utilization evaluation indicator, which comprehensively considers the impact of storage utilization and read and write speeds.

[0139] Furthermore, the following steps are included to calculate the adaptation stability index of the application software in the underlying domestic CPU hardware:

[0140] The application software's adaptation stability indicators in the underlying domestic CPU hardware include failure rate and recovery time; define the application software's time interval The number of failures in , failure rate for:

[0141] ,

[0142] in, Indicates the application software in the time interval Number of failures within It represents the failure rate, which measures the frequency of software failures per unit time;

[0143] Considering the different impacts of different faults on software usage, the fault severity coefficient is introduced , the improved failure rate is expressed as,

[0144] ,

[0145] in, Indicates the fault severity coefficient, which is used to reflect the difference in the impact of different faults on software use. The value ranges from 0 to 1. The more serious the fault, the higher the The bigger; represents the improved failure rate, taking into account the failure severity coefficient;

[0146] For the recovery time, assume that the application software The recovery time for this fault is , appear in the statistical interval The mean recovery time for:

[0147] ,

[0148] in, Indicates the application software Recovery time after a fault; Mean recovery time, which is obtained by adding up the recovery time of each fault and taking the average;

[0149] Considering the impact of fault recovery on user experience, the user impact coefficient is introduced (Determined by the extent of loss to users caused by software unavailability during fault recovery, ), the final recovery time evaluation index is expressed as,

[0150] ,

[0151] in, The user impact coefficient is determined based on the degree of loss to users caused by software unavailability during fault recovery, and its value ranges from 0 to 1. It represents the final recovery time evaluation indicator, which takes into account the average recovery time and user impact;

[0152] Furthermore, the following steps are included to calculate the specific weights of the above indicators based on the analytic hierarchy process (AHP):

[0153] The calculation based on the analytic hierarchy process (AHP) to determine the specific weights of the above indicators includes: constructing a judgment matrix, calculating the weight vector, and consistency testing;

[0154] Step 1: Construct a judgment matrix.

[0155] The definition criteria layer has indicators, namely , construct the judgment matrix ,in Indicator Relative to the indicator The importance of meeting Taking the three criteria-level indicators of instruction set compatibility, performance evaluation, and stability evaluation as examples, five experts were invited to score the importance of the indicators, and the average value was taken to obtain the judgment matrix A;

[0156] Step 2: Calculate the weight vector,

[0157] The weight vector is calculated using the sum-product method: First, each column of the judgment matrix A is normalized.

[0158] ,

[0159] in, represents the judgment matrix, Indicator Relative to the indicator The importance of meeting (reflecting the reciprocity of relative importance), (its importance compared to itself is 1); Represents the elements obtained after column normalization of the judgment matrix A, which is used for subsequent calculation of the weight vector;

[0160] Furthermore, by summing the rows of matrix A, we can get:

[0161] ,

[0162] in, Represents the intermediate value obtained by row summation, preparing for the final calculation of the weight vector;

[0163] Finally, yes Normalize to get the weight vector :

[0164] ,

[0165] in, It represents the final weight vector, which reflects the relative importance of each indicator.

[0166] Step 3: consistency check,

[0167] Calculate the maximum eigenvalue of the judgment matrix A , expressed as,

[0168] ,

[0169] in, Represents the maximum eigenvalue of the judgment matrix A, which is used to calculate the consistency index; Represents a vector No. elements.

[0170] Furthermore, the consistency index is calculated , expressed as,

[0171] ,

[0172] in, Represents the consistency index, which is used to measure the degree to which the judgment matrix deviates from consistency; Represents the random consistency index, according to the matrix order OK, as a comparison benchmark.

[0173] Calculate the consistency ratio CR, expressed as,

[0174] ,

[0175] in, Indicates the consistency ratio, through and The ratio of is obtained and used to judge whether the judgment matrix has satisfactory consistency. When , the consistency of the judgment matrix is ​​considered acceptable and the weight vector is valid.

[0176] Furthermore, the following steps are included to calculate the adaptability score of the evaluation application software in the underlying domestic CPU hardware:

[0177] After obtaining the effective weight vector, it is necessary to evaluate the adaptability score of the application software in the underlying domestic CPU hardware, which is expressed as,

[0178] ,

[0179] in, Indicates the adaptability score of the application software in the underlying domestic CPU hardware. Indicates the Technical indicators, Indicates the The weight corresponding to each indicator.

[0180] Example 2

[0181] To verify the effectiveness of the proposed strategy, consider a radar signal processing application. This software processes radar echo signals, performing operations such as range compression and azimuth focusing to produce a clear radar image. We will adapt this software to domestic CPU hardware and evaluate its performance, focusing on processing time and image quality (measured by peak sidelobe ratio and integrated sidelobe ratio).

[0182] The specific steps of the test are:

[0183] (1) Generate simulated radar echo signal: Generate simulated radar echo signal based on radar system parameters. This signal contains target information and noise.

[0184] (2) Range compression: perform range compression on the echo signal using a matched filter algorithm;

[0185] (3) Azimuth focusing: A back-projection algorithm (BP) is used to perform azimuth focusing to obtain the radar image;

[0186] (4) Image quality evaluation: Calculate the peak sidelobe ratio (PSLR) and integrated sidelobe ratio (ISLR) of the generated image;

[0187] (5) Record processing time: Run the above process multiple times on domestic CPU hardware and record the processing time each time.

[0188] In this embodiment, Figure 2 As shown, Figure 2 (a) is the original radar echo signal diagram: It shows the original echo signal received by the radar, including target information and noise, and the approximate distribution of the signal can be intuitively observed. Figure 2 (b) is the signal diagram after range compression: After range compression, the signal energy is more concentrated, which is helpful for subsequent azimuth focusing processing. Figure 2 (c) Radar image: The final radar image shows the location and shape of the target. The clarity and accuracy of the image are related to the subsequently calculated PSLR and ISLR. Figure 2 (d) shows the processing time variation of radar signal processing over multiple experiments. A relatively flat curve indicates relatively stable processing time; large fluctuations indicate resource contention or unstable algorithm complexity.

[0189] Example 3

[0190] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for evaluating the adaptation of the application software in domestic CPU hardware is implemented.

[0191] Example 4

[0192] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the adaptation evaluation method of the application software in domestic CPU hardware.

[0193] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0194] The present invention is described with reference to flowcharts and / or block diagrams of methods and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0195] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0196] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0197] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any ordinary technician in this industry can smoothly implement the present invention as shown in the drawings and described above. However, any equivalent changes, modifications and evolutions made by technicians familiar with this profession without departing from the scope of the technical solution of the present invention using the technical content disclosed above are all equivalent embodiments of the present invention. At the same time, any equivalent changes, modifications and evolutions made to the above embodiments based on the essential technology of the present invention are still within the scope of protection of the technical solution of the present invention.

[0198] The preferred embodiments of the present invention are described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Various changes can be made within the knowledge of ordinary technicians in this field without departing from the scope of the present invention.

[0199] Many other changes and modifications can be made without departing from the spirit and scope of the present invention. It should be understood that the present invention is not limited to the specific embodiments, and the scope of the present invention is defined by the appended claims.

Claims

1. The adaptation evaluation method of application software in domestic CPU hardware is characterized by: The following steps are involved: S1: Computes the instruction set compatibility indicators of the application software in the underlying domestic CPU hardware, including instruction coverage and instruction execution efficiency difference rate; S2: Computes the performance evaluation indicators of application software in the underlying domestic CPU hardware, including running speed and resource utilization; S3: Computes the adaptability stability indicators of application software in the underlying domestic CPU hardware, including failure rate and recovery time; S4: Determine the specific weights of the above indicators based on the hierarchical analysis method; S5: Evaluates the adaptability score of the application software in the underlying domestic CPU hardware; S6: Program the above steps and output the monitoring results in real time.

2. The adaptation evaluation method for application software in domestic CPU hardware according to claim 1, characterized in that: The calculation formula for the instruction coverage in S1 is: ， in, A set of application software instructions. Represents the first instructions, is the total number of application software instructions, For the domestic CPU instruction set, Indicates the first instruction in the domestic CPU instruction set instructions, is the total number of instructions in the domestic CPU instruction set, is an indicator function and satisfies, when hour ,otherwise , which are instructions in application software When it exists in the domestic CPU instruction set C, If it does not exist, then , is the instruction importance weight coefficient, The calculation formula for the instruction execution efficiency difference rate in S1 is: ， in, Is the instruction execution frequency, that is, the number of times an instruction is executed within a certain period of time, Is the standard reference CPU The execution frequency of an instruction, that is, the number of times the instruction is executed within a certain period of time; Is the standard reference CPU The execution time of the instructions; It is the first domestically produced CPU The execution frequency of the instructions; It is the first domestically produced CPU The execution time of the instructions; : Weighted instruction execution efficiency difference rate.

3. The adaptation evaluation method for application software in domestic CPU hardware according to claim 1, wherein the calculation formula for the running speed in S2 is: ， in, Represents the task weight, which is used to reflect the importance of different tasks to software performance evaluation. The value is between 0 and 1, and the sum of all task weights is 1; Indicates the total number of tasks; Indicates the The speed at which tasks are run; Represents the comprehensive running speed evaluation of multiple tasks, taking into account the running speed and weight of different tasks; The resource utilization in S2 includes CPU utilization, memory utilization, and storage utilization. The calculation formula of the CPU utilization is: ， in, Indicates the final CPU utilization evaluation index, taking into account CPU utilization and load balancing. Indicates CPU utilization, which measures how busy the CPU is during the time interval. Indicates the CPU load balancing coefficient, which is used to evaluate the load balancing of each CPU core. The closer the value is to 1, the more balanced the load is. The calculation formula of the memory utilization is: Define the total system memory size as , the memory size used by the application software is , memory utilization for: , Consider memory fragmentation rate , that is, the impact of the ratio of memory fragment size to total memory on the effective use of memory. The improved memory utilization is expressed as, ， The calculation formula of the storage utilization is: Define the total storage capacity as , the used storage capacity is , storage utilization for: ， Considering the impact of storage read and write speed on software performance, let the average storage read and write speed be , standard read and write speed is , introducing storage performance correction factor ,The final storage utilization evaluation index is expressed as, ， in, Indicates the total storage capacity; Indicates the used storage capacity; Indicates storage utilization, which measures storage resource usage; Indicates the average storage read and write speed; Indicates standard read and write speed; Indicates the storage performance correction factor, reflecting the impact of storage read and write speed on software performance; This is the final storage utilization evaluation indicator, which comprehensively considers the impact of storage utilization and read and write speed.

4. The adaptation evaluation method of application software in domestic CPU hardware according to claim 1, characterized in that: The calculation formula for the failure rate in S3 is: ， in, Indicates the fault severity coefficient, which is used to reflect the difference in the impact of different faults on software use. The value ranges from 0 to 1. The more serious the fault, the higher the The bigger; represents the failure rate, taking into account the failure severity coefficient; Indicates the application software in the time interval The number of failures that occurred within The calculation formula for the recovery time in S3 is: ， in, The user impact coefficient is determined based on the degree of loss to users caused by software unavailability during fault recovery, and its value ranges from 0 to 1. It represents the final recovery time evaluation indicator, which takes into account the average recovery time and user impact; ART stands for Mean Recovery Time, which is calculated by adding up the recovery times for each failure and taking the average: ， is the recovery time of the jth failure of the application software, Indicates that there are two or more occurrences in the statistical interval. Secondary failure.

5. The adaptation evaluation method of application software in domestic CPU hardware according to claim 1, characterized in that: The specific steps of S4 are: Step 1: Construct a judgment matrix. The definition criteria layer has indicators, namely , construct the judgment matrix ,in Indicator Relative to the indicator The importance of meeting , Taking the three criteria-level indicators of instruction set compatibility, performance evaluation, and stability evaluation as examples, five experts were invited to score the importance of the indicators, and the average value was taken to obtain the judgment matrix A; Step 2: Calculate the weight vector using the sum-product method; Step 3: consistency test, by calculating the consistency index CI and consistency ratio CR, to determine whether the judgment matrix has satisfactory consistency. When , the consistency of the judgment matrix is ​​considered acceptable and the weight vector is valid.

6. The method for evaluating the adaptation of application software in domestic CPU hardware according to claim 1, characterized in that: The calculation formula for the adaptability score in S5 is: ， in, Indicates the adaptability score of the application software in the underlying domestic CPU hardware. Indicates the Technical indicators, Indicates the The weight corresponding to each indicator.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the adaptation evaluation method of the application software in domestic CPU hardware described in any one of claims 1 to 6 is implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the adaptation evaluation method of the application software in domestic CPU hardware according to any one of claims 1 to 6 is implemented.

Images