CN116820567A

CN116820567A - Method, system, electronic device and storage medium for determining instruction consumption information

Info

Publication number: CN116820567A
Application number: CN202310774095.1A
Authority: CN
Inventors: 张学刚; 余家华; 蔡世顺
Original assignee: Hangzhou Alibaba Feitian Information Technology Co ltd
Current assignee: Hangzhou Alibaba Feitian Information Technology Co ltd
Priority date: 2023-06-27
Filing date: 2023-06-27
Publication date: 2023-09-29

Abstract

The embodiment of the application provides a method, a system, electronic equipment and a storage medium for determining instruction consumption information, and relates to the technical field of computers. The method comprises the following steps: when an application program runs in a processor, acquiring a function being executed in the processor at a target sample sampling frequency in a specified sample sampling time period to obtain a plurality of function samples; the function samples correspond to a plurality of function types; and determining instruction consumption information of the function samples corresponding to the various function types in the running process of the application program based on the function duty ratio of the function samples corresponding to the various function types in the plurality of function samples, so as to be used for analyzing the running performance of the application program in the processor. According to the scheme provided by the application, the instruction consumption information corresponding to the processor in the running process of the determined application program can be accurate to the function dimension, so that the fineness of the determined instruction consumption information is higher.

Description

Method, system, electronic device and storage medium for determining instruction consumption information

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method, a system, an electronic device, and a storage medium for determining instruction consumption information.

Background

Instruction consumption information during the running of an application has a crucial role in analyzing the running performance of the application in a processor, for example, the number of instructions consumed in the processor during the running of the application has a crucial role in analyzing the running performance of the application in the processor. Specifically, in order to analyze the running performance of an application program in a CPU (Central Processing Unit ), the number of instructions consumed in the CPU during the running of the application program is often utilized.

While the prior art can determine the number of instructions consumed in the processor during the running process of the application, the number of instructions consumed in the processor during the running process of the application determined by the prior art is often not fine enough. This results in an inability to accurately analyze the running performance of the application in the processor. In addition, the prior art also often fails to make a fine determination regarding other instruction consumption information than the number of instructions consumed in the processor during the running of the application. Therefore, how to determine the instruction consumption information in the running process of the application program becomes a technical problem to be solved urgently by those skilled in the art.

Disclosure of Invention

The embodiment of the application provides a method, a system, electronic equipment and a storage medium for determining instruction consumption information, which are used for solving one or more of the technical problems.

In a first aspect, an embodiment of the present application provides a method for determining instruction consumption information, including:

when an application program runs in a processor, acquiring a function which is being executed in the processor at a target sample sampling frequency in a specified sample sampling time period to obtain a plurality of function samples; the plurality of function samples correspond to a plurality of function types;

based on the function proportion of the function samples corresponding to the various function types in the plurality of function samples, determining instruction consumption information of the function samples corresponding to the various function types in the running process of the application program, so as to be used for analyzing the running performance of the application program in the processor.

In a second aspect, an embodiment of the present application provides a system for determining instruction consumption information, including: an instruction consumption information determining node and an instruction consumption information displaying node;

the instruction consumption information determining node is used for executing the instruction consumption information determining method provided by the embodiment of the application; transmitting instruction consumption information of function samples corresponding to various function types to an instruction consumption information display node;

The instruction consumption information display node is used for receiving and displaying the instruction consumption information of the function samples corresponding to the various function types respectively.

In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory, where the processor implements the method provided by any embodiment of the present application when the computer program is executed.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having a computer program stored therein, the computer program when executed by a processor implementing a method provided by any of the embodiments of the present application.

Compared with the prior art, the application has the following advantages:

according to the technical scheme, the instruction consumption information of the function samples corresponding to the various function types in the running process of the application program can be determined, so that the determined instruction consumption information corresponding to the application program in the running process of the application program can be accurate to the function dimension, and the determined instruction consumption information corresponding to the application program in the running process of the application program can be higher in fineness. Therefore, when the running performance of the application program in the processor is analyzed by utilizing the instruction consumption information of the function samples respectively corresponding to the various function types, the running performance of the application program in the processor can be more accurately analyzed.

In addition, the instruction consumption information of the function samples corresponding to the various function types is determined according to the function duty ratio of the function samples corresponding to the various function types in the plurality of function samples, and the plurality of function samples are obtained by collecting the executing functions in the processor at the target sample sampling frequency in the designated sample sampling time period. Therefore, the invasiveness of the source code of the application program and the processing resources required to be consumed for determining the instruction consumption information of the function samples corresponding to the various function types are reduced, and the efficiency of determining the instruction consumption information of the function samples corresponding to the various function types is improved.

The foregoing summary is for the purpose of the specification only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present application will become apparent by reference to the drawings and the following detailed description.

Drawings

In the drawings, the same reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily drawn to scale. It is appreciated that these drawings depict only some embodiments according to the disclosure and are not therefore to be considered limiting of its scope.

FIG. 1 is a schematic diagram showing an application procedure of a method for determining instruction consumption information according to an embodiment of the present application;

FIG. 2 is a flow chart illustrating a method for determining instruction consumption information provided in an embodiment of the present application;

FIG. 3 is a schematic diagram showing the relationship between a sample sampling frequency and the number of multiple functional samples provided in an embodiment of the present application;

FIG. 4 is a schematic diagram of a determining device for instruction consumption information according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a system for determining instruction consumption information provided in an embodiment of the present application; and

fig. 6 shows a block diagram of an electronic device for implementing an embodiment of the application.

Detailed Description

Hereinafter, only certain exemplary embodiments are briefly described. As will be recognized by those skilled in the pertinent art, the described embodiments may be modified in numerous different ways without departing from the spirit or scope of the present application. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive.

In order to facilitate understanding of the technical solutions of the embodiments of the present application, the following describes related technologies of the embodiments of the present application. The following related technologies may be optionally combined with the technical solutions of the embodiments of the present application, which all belong to the protection scope of the embodiments of the present application.

The embodiment of the application relates to a determination scheme of instruction consumption information, which is used for determining the instruction consumption information of function samples corresponding to various function types respectively in the running process of an application program so as to analyze the running performance of the application program in a processor. The application program is pre-selected according to the set operation performance analysis requirement, and can be configured at the terminal equipment or the server, and meanwhile, the application program can be a database, a database management system, instant messaging software, online office software and the like. Specifically, in the embodiment of the present application, the configuration environment of the application program, the type of the application program, the version of the application program, or the functions that can be implemented by the application program are not specifically limited. In addition, the processor is generally referred to as a CPU, or may be referred to as GPU (Graphics Processing Unit), and in particular, the type, specification, and model of the processor are not limited in the embodiment of the present application.

The instruction consumption information of the function samples corresponding to the various function types in the running process of the application program generally refers to the single-cycle instruction number of the function samples corresponding to the various function types in the running process of the application program. The single-cycle instruction number refers to the instruction number which can be processed in each clock cycle when the processor executes the function samples corresponding to various function types respectively in the running process of the application program. The method for determining the instruction consumption information provided in the embodiment of the present application is specifically described below by taking the instruction consumption information as a single-cycle instruction number as an example, and the instruction consumption information other than the single-cycle instruction number is not described in detail.

In general, the number of instructions per cycle refers to IPC (Instructions Per Cycle, number of instructions per cycle). Wherein the function samples are obtained by collecting the executing functions in the processor at the target sample sampling frequency during a specified sample sampling period when the application program is running in the processor. Specifically, the function being executed in the processor is collected at the target sample sampling frequency in the specified sample sampling period, so as to obtain a plurality of function samples, and the plurality of function samples correspond to a plurality of function types.

In one example, capturing the function being executed in the processor at the target sample sampling frequency over a specified sample sampling period yields 100 function samples, where the 100 function samples are assigned to 3 different function samples, denoted as: the functions of the A function, the B function and the C function, and the function numbers of the three function samples of the A function, the B function and the C function are 20, 30 and 50 respectively. In this case, the 100 function samples can be considered to correspond to 3 function types, and the 3 function types are an a function, a B function, and a C function, respectively.

During the running process of the application program, the processor can continuously call and execute the functions in the code to complete related commands, that is, the function samples are the functions which the processor calls and executes to support the running of the application program. The function being executed in the processor is collected at the target sample sampling frequency in the designated sample sampling time period, the moment of triggering the function collection operation is determined according to the target sample sampling frequency in the designated sample sampling time period, the function collection operation is triggered at the moment of triggering the function collection operation, and the function being executed in the processor is taken as a function sample when the function collection operation is triggered. Since the function being executed in the processor is collected at the target sample sampling frequency in the specified sample sampling period, the function collection operation is triggered multiple times to perform the function collection corresponding to the number of times, and therefore, the function being executed in the processor is collected at the target sample sampling frequency in the specified sample sampling period, and multiple function samples are obtained.

The principle on which the single-period instruction number of the function samples corresponding to the various function types in the running process of the application program is determined based on the function proportion of the function samples corresponding to the various function types in the plurality of function samples is the Monte Carlo sampling principle. In particular, in the embodiment of the present application, when a function being executed in a processor is collected at a specific sample sampling frequency in a specific sample sampling period during the running process of an application program, if a certain function called and executed by the processor consumes more instructions in the processor, the probability that the function is collected when performing function sampling is greater, that is, the probability that the function sampling is sampled as a function sample is greater. When the number of times of function sampling is sufficiently large in the specific sample sampling period (i.e., the specific sample sampling frequency is sufficiently large), the function ratios of the function samples corresponding to the various function types in the plurality of function samples can be considered to be consistent with the instruction number ratio of the total number of instructions consumed in the running process of the application program by the instruction numbers consumed in the processor by the function samples corresponding to the various function types. Therefore, under the condition of obtaining the total number of instructions consumed in the processor in the running process of the application program, the instruction number consumed in the processor by the function samples corresponding to the various function types can be calculated according to the function duty ratio of the function samples corresponding to the various function types in the plurality of function samples.

Also, during the running of an application, when a function being executed in a processor is collected at a specific sample sampling frequency for a specific sample sampling period, if a certain function called and executed by the processor consumes more clock cycles in the processor, the greater the probability that the function is collected when performing the function sampling, i.e., the greater the probability that the function sampling is sampled as a function sample. When the number of times of function sampling is sufficiently large in the specific sample sampling period (i.e., the specific sample sampling frequency is sufficiently large), the function ratios of the function samples corresponding to the various function types in the plurality of function samples can be considered to be consistent with the clock cycle number ratio of the clock cycle number consumed in the processor by the function samples corresponding to the various function types in the total number of clock cycles consumed in the running process of the application program. Therefore, under the condition of obtaining the total number of clock cycles consumed in the processor in the running process of the application program, the clock cycles consumed in the processor by the function samples corresponding to the function types can be calculated according to the function duty ratios of the function samples corresponding to the function types in the function samples.

Under the condition that the instruction numbers consumed in the processor by the function samples corresponding to the function types and the clock cycles consumed in the processor by the function samples corresponding to the function types are calculated, the single-cycle instruction numbers of the function samples corresponding to the function types in the running process of the application program can be further calculated.

In one example, the plurality of function samples includes 500 function samples, and the 500 function samples are assigned to 5 different function samples, respectively denoted as: a first function sample, a second function sample, a third function sample, a fourth function sample, and a fifth function sample. If the first, second, third, fourth and fifth function samples are respectively: 50. 100, 150, 100, it may be determined that the function duty ratios corresponding to the 5 different function samples in the 500 function samples are: 1/10, 1/5, 3/10 and 1/5. In this case, if the total number of instructions consumed in the processor during the running process of the application program is 5000, the number of instructions consumed in the processor by the function samples corresponding to the various function types can be calculated as follows: 500. 1000, 1500, and 1000. Correspondingly, if the total number of clock cycles consumed in the processor during the running process of the application program is 20000, the number of clock cycles consumed in the processor by the function samples corresponding to the various function types can be calculated as follows: 2000. 4000, 6000 and 4000.

Under the condition that the instruction number consumed in the processor by the function samples corresponding to the various function types and the clock cycle number consumed in the processor by the function samples corresponding to the various function types are obtained through calculation, the single-cycle instruction number of the function samples corresponding to the various function types in the running process of the application program can be further calculated and obtained, wherein the single-cycle instruction number is as follows: 0.25, 0.25 and 0.25.

In order to more clearly show the method for determining the instruction consumption information provided in the embodiment of the present application, an application example of the method for determining the instruction consumption information provided in the embodiment of the present application is first introduced, where the method for determining the instruction consumption information is used for determining the single-period instruction numbers of function samples corresponding to each function type in the running process of the database, so as to analyze the influence of each function type of the corresponding function sample on the running bottleneck of the database when the database runs in the processor, where the database is configured at the server. In this case, the instruction consumption information refers to a single-cycle instruction number, the application program refers to a database configured at the server side, and the analysis of the running performance of the application program in the processor refers to the analysis of the influence of function samples corresponding to various function types on the running bottleneck of the database when the database runs in the processor.

In order to analyze the influence of function samples corresponding to various function types on the operation bottleneck of the database when the database operates in the processor, a function sampling module pre-configured in a server side can be utilized first, and in the operation process of the database, the function being executed in the processor is collected at a target sample sampling frequency in a specified sample sampling time period to obtain a plurality of function samples. After the function sampling module samples a plurality of function samples, the function samples are sent to a pre-configured instruction consumption information determining module in the server.

After the instruction consumption information determining module obtains the plurality of function samples provided by the function sampling module, the single-period instruction number of the function samples corresponding to the function types in the running process of the database can be determined based on the function duty ratio of the function samples corresponding to the function types in the function samples. After determining the single-period instruction numbers of the function samples corresponding to the various function types, the instruction consumption information determining module sends the single-period instruction numbers of the function samples corresponding to the various function types to a pre-configured operation performance analyzing module in the server.

After receiving the single-period instruction numbers of the function samples corresponding to the various function types provided by the instruction consumption information determining module, the operation performance analyzing module analyzes the influence of the function samples corresponding to the various function types on the operation bottleneck of the database when the database operates in the processor according to the single-period instruction numbers of the function samples corresponding to the various function types.

The method for determining the instruction consumption information provided by the embodiment of the application can determine the single-period instruction number of the function samples respectively corresponding to various function types in the database operation process, so that the determined instruction number consumed in the processor in the database operation process can be accurate to the function dimension, and the determined instruction number consumed in the processor in the database operation process can be higher in fineness. Therefore, when the operation performance of the database in the processor is analyzed by utilizing the single-period instruction data of the function samples corresponding to the various function types, the influence of the function samples corresponding to the various function types on the operation bottleneck of the database when the database is operated in the processor can be more accurately analyzed.

In addition, the single-period instruction number of the function samples corresponding to the various function types is determined according to the function duty ratio of the function samples corresponding to the various function types in the plurality of function samples, and the plurality of function samples are obtained by collecting the functions being executed in the processor at the target sample sampling frequency in the designated sample sampling time period. Therefore, the invasiveness to the source code of the database and the processing resources required to be consumed for determining the single-cycle instruction number of the function samples corresponding to the various function types are reduced, and the efficiency of determining the single-cycle instruction number of the function samples corresponding to the various function types is improved.

It should be noted that the above application examples of the method for determining instruction consumption information provided in the embodiment of the present application are for ease of understanding and are not intended to limit the method for determining instruction consumption information provided in the embodiment of the present application. Specifically, an application scenario of the method for determining instruction consumption information provided in the embodiment of the present application is not specifically limited.

In addition, in the determination scheme of the instruction consumption information provided in the embodiment of the present application, the corresponding execution body may be a functional module in a software form (such as a functional module configured in an application program and having a function of determining the instruction number), a Virtual Machine (VM), a cloud server, or a hardware device (such as a server, a terminal device) having a function of determining the instruction consumption information. In the embodiment of the present application, the execution subject corresponding to the determination scheme of the instruction consumption information is not particularly limited.

The following describes the technical scheme of the present application and how the technical scheme of the present application solves the above technical problems in detail with specific embodiments. The following related technologies may be optionally combined with the technical solutions of the embodiments of the present application, which all belong to the protection scope of the embodiments of the present application, and the same or similar concepts or processes may not be described in some embodiments.

Fig. 2 shows a flow chart of a method 200 for determining instruction consumption information provided in an embodiment of the application, which may include steps S201-S202.

In step S201, when an application program runs in a processor, acquiring a function being executed in the processor at a target sample sampling frequency in a specified sample sampling period to obtain a plurality of function samples; the plurality of function samples corresponds to a plurality of function types.

The application program can be a database, a database management system, instant messaging software, online office software and the like. The processor is typically a CPU, but may also be a GPU, or the like.

The designated sample sampling time period and the target sample sampling frequency can be obtained by screening in a plurality of candidate sample collection time periods and sample sampling frequencies respectively corresponding to the candidate sample collection time periods. Acquiring the function being executed in the processor at the target sample sampling frequency during the specified sample sampling period may refer to taking the candidate function samples acquired at the target sample sampling frequency during the specified sample sampling period as a plurality of function samples in the case where the specified sample sampling period and the target sample sampling frequency are determined.

According to the Monte Carlo sampling principle, on the premise that no function sample is lost, the more the number of the plurality of function samples is sampled, the higher the function proportion of the function samples corresponding to each function type in the plurality of function samples is, and the higher the consistency between the instruction number proportion of the instruction number consumed in the total instruction number by the function samples corresponding to each function type in the processor is. Similarly, the greater the number of the plurality of function samples, the higher the consistency between the function ratios of the function samples corresponding to the respective function types in the plurality of function samples and the clock cycle number ratios of the clock cycle numbers consumed in the processor by the function samples corresponding to the respective function types in the total number of clock cycles.

In practical applications, due to factors such as processor performance limitation and application running condition, when the sample sampling frequency is large, if the function sampling is performed at the sample sampling frequency, there may be a case that the function sample is lost. In this case, the relationship between the sample sampling frequency and the number of the plurality of function samples is approximately as shown in fig. 3, and fig. 3 shows a schematic diagram of the relationship between the sample sampling frequency and the number of the plurality of function samples, wherein the X-axis is used to represent the sample sampling frequency and the Y-axis is used to represent the number of the plurality of function samples. As shown in fig. 3, when the sample sampling frequency is relatively small, the number of the plurality of function samples reaches a peak value as the sample sampling frequency increases, in which case, the sample sampling frequency is further increased, and the number of the plurality of function samples is continuously decreased.

As is clear from the above, the relation between the sample sampling frequency and the number of the plurality of function samples is not a proportional relation, so that the number of the plurality of function samples can be increased, so that the number of single-cycle instructions of the function samples corresponding to each function type can be more accurately determined based on the function duty of the function samples corresponding to each function type in the plurality of function samples, and the sample sampling frequency cannot be simply increased. In this case, in order to make the number of the plurality of function samples larger, function collection may be performed by using different sample collection frequencies in a plurality of candidate sample collection time periods in the running process of the application program, so as to obtain candidate function samples corresponding to each candidate sample collection time period. And then determining a designated sample sampling time period and a target sample sampling frequency according to the candidate function samples respectively corresponding to the candidate sample acquisition time periods. And finally, screening candidate function samples acquired at the target sample sampling frequency in the designated sample sampling time period from candidate function samples respectively corresponding to the candidate sample sampling time periods.

In the application program operation process, a plurality of candidate sample collection time periods are respectively subjected to function collection by adopting different sample collection frequencies, and the step of obtaining candidate function samples respectively corresponding to the candidate sample collection time periods is to firstly select a plurality of candidate sample collection time periods with the same duration in the application program operation process, and respectively adopt different sample collection frequencies to carry out function collection in each candidate sample collection time period so as to obtain candidate function samples respectively corresponding to the candidate sample collection time periods.

Determining the designated sample sampling time period and the target sample sampling frequency according to the candidate function samples corresponding to each candidate sample collection time period refers to determining the candidate function sample with the largest function number among the candidate function samples corresponding to a plurality of candidate sample collection time periods according to the number of the candidate function samples. Then, the candidate sample collection time period and the sample sampling frequency matched with the candidate function sample with the largest function number are determined. And finally, determining the candidate sample collection time period and the sample sampling frequency matched with the candidate function sample with the largest function number as the designated sample sampling time period and the target sample sampling frequency.

Screening candidate function samples acquired at the target sample sampling frequency in the designated sample sampling time period from candidate function samples corresponding to each candidate sample sampling time period respectively as a plurality of function samples means that the candidate function sample with the largest function number is determined as the plurality of function samples in the candidate function samples corresponding to each candidate sample sampling time period respectively.

In one possible implementation manner, when obtaining the candidate function samples corresponding to each candidate sample collection time period, function collection may be performed at a set sample collection frequency in a first candidate sample collection time period of the plurality of candidate sample collection time periods, so as to obtain a candidate function sample corresponding to the first candidate sample collection time period. And then, based on the set sample collection frequency, sequentially adjusting sample collection frequencies corresponding to other candidate sample collection time periods by using a dichotomy, and carrying out function collection in the other candidate sample collection time periods at the corresponding sample collection frequencies to obtain candidate function samples respectively corresponding to the other candidate sample collection time periods.

The set sample collection frequency may be pre-configured for the processor and the running condition of the application in the processor, that is, the set sample collection frequency may be configured according to the prior value.

Based on the set sample collection frequency, sequentially adjusting the sample collection frequencies corresponding to other candidate sample collection time periods by using a dichotomy means that the set sample collection frequency is increased by a certain proportion after the candidate function sample corresponding to the first candidate sample collection time period is obtained, so as to determine the sample collection frequency in the second candidate sample collection time period. And then, in the second candidate sample collection time period, carrying out function collection at the corresponding determined sample collection frequency to obtain candidate function samples corresponding to the second candidate sample collection time period, and if the number of the candidate function samples corresponding to the second candidate sample collection time period is increased compared with the number of the candidate function samples corresponding to the first candidate sample collection time period, carrying out a certain proportion of increase on the sample collection frequency in the second candidate sample collection time period so as to determine the sample collection frequency in the third candidate sample collection time period. And if the number of candidate function samples corresponding to the second candidate sample collection time period is reduced compared with the number of candidate function samples corresponding to the first candidate sample collection time period, reducing the sample collection frequency in the second candidate sample collection time period by a certain proportion so as to determine the sample collection frequency in the third candidate sample collection time period. And continuously adopting the sample collection frequency adjustment mode to adjust the sample collection frequency in the subsequent candidate sample collection time period.

In order to reduce the time required to obtain the candidate function samples corresponding to each candidate sample collection time period, so as to further improve the efficiency of determining the single-cycle instruction number of the function samples corresponding to each function type, the number of the plurality of candidate sample collection time periods can be limited. That is, the number of adjustments to the sample acquisition frequency adjustment can be limited.

The specified sample sampling period and the target sample sampling frequency may also be preconfigured based on the a priori value. Specifically, in order to reduce the time required to obtain candidate function samples corresponding to each candidate sample collection time period, so as to further improve the efficiency of determining the single-period instruction number of the function samples corresponding to each function type, and collect the executing function in the processor at the target sample sampling frequency in the specified sample collection time period, when obtaining a plurality of function samples, the target sample collection frequency can be obtained for an application program and the processor in a plurality of sample collection frequencies which are configured in advance. Then, a designated sample acquisition time period is selected in the running process of the application program according to the prior value. And finally, carrying out function acquisition at the target sample acquisition frequency in a designated sample acquisition time period to obtain a plurality of function samples.

Among the preconfigured sample collection frequencies, for the application program and the processor, acquiring the target sample collection frequency means that a preconfigured sample collection frequency set is acquired first, and then, for the application program and the processor, the target sample collection frequency is screened out from the sample collection frequency set. The sample collection frequency set is recorded with a plurality of sample collection frequencies and processors and application programs respectively corresponding to the sample collection frequencies.

In one possible implementation, the target sample acquisition frequency may be configured as a trigger frequency in the processor for monitoring interrupt events for more convenient function acquisition. Typically, the performance monitoring interrupt event is referred to as PMI (Performance Monitoring Interrupt ). In the case where the target sample collection frequency is configured as the trigger frequency of the performance monitoring interrupt event in the processor, collecting the functions being executed in the processor at the target sample collection frequency during the specified sample collection period, obtaining a plurality of function samples means that, during the specified sample collection period, if the performance monitoring interrupt event triggers, the functions being executed in the processor are collected. Specifically, when the performance monitoring interrupt event triggers, the executing code of the processor can be determined, and by reading the executing code of the processor, the executing function in the processor can be determined.

In one example, to be able to accurately locate a function executing in a processor, when reading code being executed by the processor, and determining the function being executed in the processor, the code being executed by the processor may be read first, the function context being executed by the processor when the performance monitoring interrupt event triggers is determined, and then the function being executed in the processor is determined based on the function context. In the case of determining the context of the function being executed by the processor, the function being executed in the processor can be accurately located.

In the method for determining instruction consumption information provided in the embodiment of the present application, after obtaining a plurality of function samples, step S202 is further executed, and in step S202, instruction consumption information of the function samples corresponding to each function type in the running process of the application program is determined based on the function duty ratios of the function samples corresponding to each function type in the plurality of function samples, so as to be used for analyzing the running performance of the application program in the processor.

In the embodiment of the present application, the instruction consumption information of the function samples corresponding to each function type in the running process of the application program generally refers to the single-period instruction number of the function samples corresponding to each function type in the running process of the application program, and may also be other types of instruction consumption numbers. In this case, determining the instruction consumption information of the function samples corresponding to the respective function types in the running process of the application program based on the function ratios of the function samples corresponding to the respective function types in the plurality of function samples refers to determining the single-cycle instruction numbers of the function samples corresponding to the respective function types in the running process of the application program based on the function ratios of the function samples corresponding to the respective function types in the plurality of function samples.

When the number of times of function sampling is enough in the sample sampling time period, the function proportion of the function samples corresponding to the various function types in the plurality of function samples can be considered to be consistent with the instruction proportion of the instruction number consumed in the processor by the function samples corresponding to the various function types in the total instruction number, and meanwhile, the function proportion of the function samples corresponding to the various function types in the plurality of function samples can also be considered to be consistent with the clock cycle proportion of the clock cycle number consumed in the processor by the function samples corresponding to the various function types in the total clock cycle number. Therefore, when determining the single-period instruction number of the function samples respectively corresponding to the various function types in the running process of the application program based on the function duty ratios of the function samples respectively corresponding to the various function types in the plurality of function samples, the instruction number and the clock cycle number consumed in the processor by the function samples respectively corresponding to the various function types in the running process of the application program can be determined firstly based on the function duty ratios of the function samples respectively corresponding to the various function types in the plurality of function samples. Then, determining the single-period instruction number of the function samples corresponding to the various function types according to the instruction number and clock cycle number consumed in the processor by the function samples corresponding to the various function types.

Determining the instruction number and clock cycle number consumed in the processor by the function samples corresponding to the function types in the running process of the application program based on the function duty ratio of the function samples corresponding to the function types in the function samples, wherein the instruction number and clock cycle number consumed in the processor by the function samples corresponding to the function types in the running process of the application program are firstly obtained, then, the instruction number and clock cycle number consumed in the processor by the function samples corresponding to the function types in the function samples are calculated according to the instruction number and clock cycle number, and the function duty ratio of the function samples corresponding to the function types in the function samples is calculated.

Specifically, based on the function ratios of the function samples corresponding to the various function types in the plurality of function samples, the instruction number ratio of the instruction number consumed in the instruction total number by the function samples corresponding to the various function types in the processor can be determined, and the clock cycle number ratio of the clock cycle number consumed in the processor by the function samples corresponding to the various function types in the clock cycle total number can be determined. Under the condition that the instruction number duty ratio of the function samples corresponding to the various function types respectively and the clock cycle total number of the function samples corresponding to the various function types respectively are determined, the instruction number consumed in the processor of the function samples corresponding to the various function types respectively can be determined based on the instruction number duty ratio of the function samples corresponding to the instruction total number and the various function types respectively, and the clock cycle number duty ratio of the function samples corresponding to the various function types respectively are determined based on the clock cycle total number and the clock cycle number duty ratio of the function samples corresponding to the various function types respectively, so that the clock cycle number consumed in the processor of the function samples corresponding to the various function types respectively is determined.

The total number of instructions and clock cycles consumed in the processor during the running of the application may be obtained by reading performance monitoring data obtained from the PMU (Performance Monitor Unit, performance monitoring unit) of the processor. Specifically, the performance monitoring data records the number of events occurring inside the processor, such as the number of instructions consumed and the number of clock cycles.

In the embodiment of the application, after determining the instruction consumption information of the function samples corresponding to the various function types in the running process of the application program, the instruction consumption information of the function samples corresponding to the various function types can be further displayed.

The method for determining instruction consumption information provided in the embodiment of the application,

the instruction consumption information of the function samples corresponding to the various function types in the running process of the application program can be determined, so that the determined instruction consumption information corresponding to the processor in the running process of the application program can be accurate to the function dimension, and the determined instruction consumption information corresponding to the processor in the running process of the application program can be higher in fineness. Therefore, when the running performance of the application program in the processor is analyzed by utilizing the instruction consumption information of the function samples respectively corresponding to the various function types, the running performance of the application program in the processor can be more accurately analyzed.

Corresponding to the application example of the method and the method for determining the instruction consumption information provided by the embodiment of the application, the embodiment of the application also provides a device for determining the instruction consumption information. Referring to fig. 4, which is a block diagram illustrating a configuration of an apparatus 400 for determining instruction consumption information according to an embodiment of the present application, the apparatus 400 may include:

A function sampling module 401, configured to collect, when an application program is running in the processor, a function being executed in the processor at a target sample sampling frequency in a specified sample sampling period, so as to obtain a plurality of function samples; the plurality of function samples correspond to a plurality of function types;

the instruction consumption information determining module 402 is configured to determine instruction consumption information of function samples corresponding to various function types during an application running process based on function duty ratios of the function samples corresponding to the various function types in the plurality of function samples, so as to analyze running performance of the application in the processor.

In one possible implementation, the function sampling module 401 includes:

the function sampling submodule is used for respectively adopting different sample collection frequencies to perform function collection in a plurality of candidate sample collection time periods in the running process of the application program to obtain candidate function samples respectively corresponding to the candidate sample collection time periods;

the sampling condition determining submodule is used for determining a designated sample sampling time period and a target sample sampling frequency according to candidate function samples respectively corresponding to each candidate sample acquisition time period;

and the function sample screening submodule is used for screening candidate function samples acquired at the target sample sampling frequency in the designated sample sampling time period from candidate function samples respectively corresponding to each candidate sample acquisition time period as a plurality of function samples.

In one possible implementation, the function sampling submodule includes:

the first sampling submodule is used for carrying out function acquisition at a set sample acquisition frequency in a first candidate sample acquisition time period in a plurality of candidate sample acquisition time periods to obtain candidate function samples corresponding to the first candidate sample acquisition time period;

the second sampling submodule is used for sequentially adjusting sample acquisition frequencies corresponding to other candidate sample acquisition time periods by using a dichotomy based on the set sample acquisition frequency, and carrying out function acquisition with the corresponding sample acquisition frequencies in the other candidate sample acquisition time periods to obtain candidate function samples respectively corresponding to the other candidate sample acquisition time periods.

In one possible implementation, the function sampling module 401 includes:

the sample acquisition frequency acquisition sub-module is used for acquiring target sample acquisition frequency aiming at an application program and a processor;

the sample collection time period selection submodule is used for selecting a designated sample collection time period in the running process of the application program;

and the third sampling submodule is used for carrying out function acquisition at the target sample acquisition frequency in a specified sample acquisition time period to obtain a plurality of function samples.

In one possible implementation, the sample acquisition frequency acquisition submodule includes:

the sample acquisition frequency set acquisition sub-module is used for acquiring a pre-configured sample acquisition frequency set; a plurality of sample collection frequencies and a processor and an application program corresponding to each sample collection frequency are recorded in the sample collection frequency set;

and the sample acquisition frequency screening sub-module is used for screening out target sample acquisition frequency from the sample acquisition frequency set aiming at the application program and the processor.

In one possible implementation, the target sample acquisition frequency includes a trigger frequency of performance monitoring interrupt events in the processor; the function sampling module 401 includes:

and a fourth sampling submodule, configured to collect a function being executed in the processor if the performance monitoring interrupt event triggers during a specified sample collection time period.

In one possible implementation, the fourth sampling submodule includes:

a code determination submodule for determining the code being executed by the processor when the performance monitoring interrupt event triggers;

and the code reading sub-module is used for reading the executing code of the processor and determining the executing function in the processor.

In one possible implementation, the code reading submodule includes:

the function context determining submodule is used for reading the codes being executed by the processor and determining the function context executed by the processor when the performance monitoring interrupt event is triggered;

and a fifth sampling submodule for determining a function being executed in the processor based on the function context.

In one possible implementation, the instruction consumption information includes a single cycle instruction number; the instruction consumption information determination module 402 includes:

the event number determining submodule is used for determining the instruction number and clock cycle number consumed in the processor by the function samples corresponding to the various function types in the running process of the application program based on the function duty ratio of the function samples corresponding to the various function types in the plurality of function samples;

and the single-period instruction number calculation sub-module is used for determining the single-period instruction number of the function samples corresponding to the various function types according to the instruction number and the clock cycle number consumed in the processor by the function samples corresponding to the various function types.

In one possible implementation, the event number determination submodule includes:

the event number acquisition sub-module is used for acquiring the total number of instructions consumed in the processor and the total number of clock cycles in the running process of the application program;

The event number calculation sub-module is used for calculating the instruction number and clock cycle number of the function samples corresponding to the various function types in the processor according to the function duty ratio of the function samples corresponding to the various function types in the plurality of function samples.

In one possible implementation, the apparatus further includes:

and the single-period instruction number display module is used for displaying the instruction consumption information of the function samples corresponding to the various function types respectively to comprise the single-period instruction number after determining the single-period instruction number of the function samples corresponding to the various function types respectively in the running process of the application program.

The functions of each module in each device of the embodiment of the present application may be referred to the corresponding descriptions in the above methods, and have corresponding beneficial effects, which are not described herein.

Corresponding to the application example of the method provided by the embodiment of the application and the method for determining the instruction consumption information provided by the embodiment of the application, the embodiment of the application also provides a system for determining the instruction consumption information. Referring now to FIG. 5, which is a block diagram illustrating a domain name resolution system 500 according to an embodiment of the application, the system 500 may include: instruction consumption information determination node 501 and instruction consumption information presentation node 502;

An instruction consumption information determining node 501, configured to execute the method for determining instruction consumption information provided by the embodiment of the present application; transmitting the single-period instruction numbers of the function samples corresponding to the various function types to the instruction consumption information display node 502;

the instruction consumption information display node 502 is configured to receive and display a single-cycle instruction number of function samples corresponding to each function type.

In the embodiment of the present application, the instruction consumption information determining node 501 is generally referred to as a server, and the instruction consumption information displaying node 502 may be a device terminal or a data displaying device configured on the server.

The functions of each node in each device of the embodiments of the present application may be referred to the corresponding descriptions in the above methods, and have corresponding beneficial effects, which are not described herein.

Fig. 6 is a block diagram of an electronic device used to implement an embodiment of the application. As shown in fig. 6, the electronic device includes: a memory 601 and a processor 602, the memory 601 storing a computer program executable on the processor 602. The processor 602, when executing the computer program, implements the methods in the above embodiments. The number of memories 601 and processors 602 may be one or more.

The electronic device further includes:

and the communication interface 603 is used for communicating with external equipment and performing data interaction transmission.

If the memory 601, the processor 602, and the communication interface 603 are implemented independently, the memory 601, the processor 602, and the communication interface 603 may be connected to each other and perform communication with each other through buses. The bus may be an industry standard architecture (Industry Standard Architecture, ISA) bus, an external device interconnect (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in fig. 6, but not only one bus or one type of bus.

Alternatively, in a specific implementation, if the memory 601, the processor 602, and the communication interface 603 are integrated on a chip, the memory 601, the processor 602, and the communication interface 603 may perform communication with each other through internal interfaces.

The embodiment of the application provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the method provided in the embodiment of the application.

The embodiment of the application also provides a chip, which comprises a processor and is used for calling the instructions stored in the memory from the memory and running the instructions stored in the memory, so that the communication equipment provided with the chip executes the method provided by the embodiment of the application.

The embodiment of the application also provides a chip, which comprises: the input interface, the output interface, the processor and the memory are connected through an internal connection path, the processor is used for executing codes in the memory, and when the codes are executed, the processor is used for executing the method provided by the application embodiment.

It should be appreciated that the processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or any conventional processor or the like. It is noted that the processor may be a processor supporting an advanced reduced instruction set machine (Advanced RISC Machines, ARM) architecture.

Further, optionally, the memory may include a read-only memory and a random access memory, and may further include a nonvolatile random access memory. The memory may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), programmable ROM (PROM), erasable Programmable ROM (EPROM), electrically Erasable EPROM (EEPROM), or flash Memory, among others. Volatile memory can include random access memory (Random Access Memory, RAM), which acts as external cache memory. By way of example, and not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic RAM (Dynamic Random Access Memory, DRAM), synchronous DRAM (SDRAM), double Data Rate Synchronous DRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous DRAM (SLDRAM), and Direct RAM (DR RAM).

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions in accordance with the present application are fully or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. Computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

Any process or method description in a flowchart or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process. And the scope of the preferred embodiments of the present application includes additional implementations in which functions may be performed in a substantially simultaneous manner or in an opposite order from that shown or discussed, including in accordance with the functions that are involved.

Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.

It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the methods of the embodiments described above may be performed by a program that, when executed, comprises one or a combination of the steps of the method embodiments, instructs the associated hardware to perform the method.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules described above, if implemented in the form of software functional modules and sold or used as a stand-alone product, may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.

The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that various modifications and substitutions are possible within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.

Claims

1. A method of determining instruction consumption information, comprising:

when an application program runs in a processor, acquiring a function being executed in the processor at a target sample sampling frequency in a specified sample sampling time period to obtain a plurality of function samples; the function samples correspond to a plurality of function types;

and determining instruction consumption information of the function samples corresponding to the various function types in the running process of the application program based on the function duty ratio of the function samples corresponding to the various function types in the plurality of function samples, so as to be used for analyzing the running performance of the application program in the processor.

2. The method of claim 1, wherein the acquiring the function being executed in the processor at the target sample sampling frequency over a specified sample sampling period of time, results in a plurality of function samples comprising:

In a plurality of candidate sample collection time periods in the running process of the application program, respectively adopting different sample collection frequencies to perform function collection to obtain candidate function samples respectively corresponding to the candidate sample collection time periods;

determining the designated sample sampling time period and the target sample sampling frequency according to candidate function samples respectively corresponding to each candidate sample acquisition time period;

and screening candidate function samples acquired at the target sample sampling frequency in the designated sample sampling time period from candidate function samples respectively corresponding to the candidate sample sampling time periods.

3. The method of claim 2, wherein the performing function collection with different sample collection frequencies in the multiple candidate sample collection time periods during the application running process, and obtaining candidate function samples corresponding to the candidate sample collection time periods respectively include:

in a first candidate sample collection time period in the candidate sample collection time periods, performing function collection at a set sample collection frequency to obtain a candidate function sample corresponding to the first candidate sample collection time period;

And sequentially adjusting sample acquisition frequencies corresponding to other candidate sample acquisition time periods by using a dichotomy based on the set sample acquisition frequency, and carrying out function acquisition with the corresponding sample acquisition frequencies in the other candidate sample acquisition time periods to obtain candidate function samples respectively corresponding to the other candidate sample acquisition time periods.

4. The method of claim 1, wherein the acquiring the function being executed in the processor at the target sample sampling frequency over a specified sample sampling period of time, results in a plurality of function samples comprising:

acquiring the target sample acquisition frequency for the application program and the processor;

selecting the designated sample collection time period in the running process of the application program;

and carrying out function acquisition at the target sample acquisition frequency in the designated sample acquisition time period to obtain the plurality of function samples.

5. The method of claim 4, wherein the acquiring the target sample acquisition frequency for the application and the processor comprises:

acquiring a pre-configured sample acquisition frequency set; the sample collection frequency set is recorded with a plurality of sample collection frequencies and a processor and an application program corresponding to each sample collection frequency respectively;

And screening the target sample acquisition frequency from the sample acquisition frequency set aiming at the application program and the processor.

6. The method of claim 1, wherein the target sample acquisition frequency comprises a trigger frequency of performance monitoring interrupt events in the processor; the acquiring the function being executed in the processor at the target sample sampling frequency in the specified sample sampling time period, and obtaining a plurality of function samples includes:

and acquiring the executing function in the processor in the specified sample acquisition time period if the performance monitoring interrupt event triggers.

7. The method of claim 6, wherein the acquiring the function being executed in the processor if the performance monitoring interrupt event triggers during the specified sample acquisition period comprises:

determining code being executed by the processor when the performance monitoring interrupt event triggers;

and reading the executing code of the processor and determining the executing function in the processor.

8. The method of claim 7, wherein the reading code being executed by the processor, determining a function being executed in the processor comprises:

Reading the executing code of the processor, and determining the function context executed by the processor when the performance monitoring interrupt event is triggered;

based on the function context, a function being executed in the processor is determined.

9. The method of claim 1, wherein the instruction consumption information comprises a single cycle instruction number; the determining the instruction consumption information of the function samples corresponding to the function types in the running process of the application program based on the function duty ratio of the function samples corresponding to the function types in the function samples comprises the following steps:

determining the instruction number and clock cycle number consumed in the processor by the function samples respectively corresponding to the various function types in the running process of the application program based on the function duty ratio of the function samples respectively corresponding to the various function types in the plurality of function samples;

and determining the single-period instruction number of the function samples corresponding to the various function types according to the instruction number and the clock cycle number consumed in the processor by the function samples corresponding to the various function types.

10. The method of claim 9, wherein the determining, based on the function duty ratios of the function samples corresponding to the respective function types in the plurality of function samples, the number of instructions and clock cycles consumed in the processor by the respective function samples corresponding to the respective function types during the running of the application program comprises:

Acquiring the total number of instructions consumed in the processor and the total number of clock cycles in the running process of the application program;

and calculating the instruction number and clock cycle number consumed in the processor by the function samples corresponding to the various function types respectively according to the function duty ratio of the function samples corresponding to the various function types in the plurality of function samples.

11. The method of claim 1, wherein after determining the instruction consumption information of the function samples corresponding to the respective function types during the running of the application, the method further comprises:

instruction consumption information of function samples corresponding to the various function types is displayed.

12. A system for determining instruction consumption information, comprising: an instruction consumption information determining node and an instruction consumption information displaying node;

the instruction consumption information determination node for performing the method of any of claims 1-10; transmitting instruction consumption information of function samples corresponding to various function types to the instruction consumption information display node;

13. An electronic device comprising a memory, a processor and a computer program stored on the memory, the processor implementing the method of any one of claims 1-11 when the computer program is executed.

14. A computer readable storage medium having stored therein a computer program which, when executed by a processor, implements the method of any of claims 1-11.