Method and system for intelligently evaluating performance of storage chip under grid array packaging

Abstract

The invention relates to the technical field of storage chips, and discloses an intelligent evaluation method and system for the performance of a storage chip under grid array packaging, and the method comprises the steps: determining a performance monitoring point on the storage chip through a performance analysis sample; identifying data probability distribution of the unstable data, and performing data smoothing processing on the unstable data by using the data probability distribution; querying a current scene corresponding to the performance analysis index; analyzing the scene similarity between the current scene and the contrast scene, calculating the contrast demand degree of the contrast scene for the contrast analysis index, and calculating the current demand degree of the current scene for the performance analysis index; identifying a contrast index of the contrast chip from the contrast analysis indexes by using the contrast demand degree, identifying a current index of the storage chip from the performance analysis indexes, and analyzing contrast performance corresponding to the contrast index; a performance increase ratio of the current performance relative to the control performance is calculated. According to the invention, the performance of a new chip relative to an old chip can be evaluated based on unstable test data.

Description

Technical Field

[0001] The invention relates to a method and system for intelligently evaluating the performance of a storage chip under grid array packaging, and belongs to the technical field of storage chips. Background Art

[0002] Nowadays, the pins of the memory chip under the land grid array package (LGA package) have changed from the ball shape of the BGA package to the contact point, so the processor using the LGA775 interface is also different from other products in the installation method. It cannot use pins to fix the contact, but requires a mounting bracket to fix it so that the CPU can be correctly pressed on the elastic tentacles exposed by the Socket. The principle is the same as the BGA package, except that the BGA is soldered, while the LGA can release the bracket at any time to replace the chip.

[0003] At present, the chip performance evaluation process needs to be based on a series of data obtained from chip testing. If the performance of the chip cannot be judged by the test data at a certain moment, it is necessary to collect data within a continuous period for analysis. When analyzing the data within a continuous period, it cannot be guaranteed that the data within the continuous period is stable data with a small variation range. If the variation range between the data at different moments is large and unstable, it will affect the performance analysis. Secondly, different chips are applicable to different scenarios. If a chip A is currently applicable to scenario A and performs well in scenario A, and chip B is applicable to scenario B and performs poorly in scenario A, it cannot be used to determine that the performance of chip A is better than that of chip B. Therefore, when chips applicable to different scenarios are directly compared, the performance of the chip cannot be correctly determined.

[0004] Therefore, there is an urgent need for a solution that can evaluate the performance of new chips relative to old chips based on unstable test data. Summary of the invention

[0005] The present invention provides a method and system for intelligently evaluating the performance of a storage chip in a grid array package, the main purpose of which is to evaluate the performance of a new chip relative to an old chip based on unstable test data.

[0006] To achieve the above object, the present invention provides a method for intelligently evaluating the performance of a memory chip in a grid array package, comprising: Determine a performance analysis dimension of a memory chip in a grid array package, select a performance analysis sample of the memory chip based on the performance analysis dimension, apply the performance analysis sample to the memory chip, and determine a performance monitoring point on the memory chip through the performance analysis sample; Collecting performance monitoring data of the storage chip at the performance monitoring point, dividing the performance monitoring data into stable data and unstable data, identifying the data probability distribution of the unstable data, and performing data smoothing processing on the unstable data using the data probability distribution to obtain smoothed data; Using the stable data and the smoothed data as performance analysis indicators of the storage chip, querying a current scene corresponding to the performance analysis indicator, acquiring a reference chip of the storage chip, and identifying a reference scene corresponding to the reference analysis indicator of the reference chip; Analyzing the scene similarity between the current scene and the control scene, calculating the control requirement of the control scene for the control analysis indicator, and calculating the current requirement of the current scene for the performance analysis indicator according to the scene similarity and the control requirement; Using the control requirement to identify the control index of the control chip from the control analysis index, using the current requirement to identify the current index of the storage chip from the performance analysis index, analyzing the control performance corresponding to the control index, and analyzing the current performance corresponding to the current index; A performance improvement ratio of the current performance relative to the control performance is calculated, and the performance improvement ratio is used as a performance intelligent evaluation result of the storage chip.

[0007] Optionally, determining the performance monitoring point on the storage chip by using the performance analysis sample includes: Using a preset data monitoring device to monitor first test data at different chip positions of the memory chip; Calculating the data correlation between the first test data at every two positions in the first test data; When the data correlation is not greater than a preset correlation, setting a first monitoring point on different chip positions of the storage chip; When the data correlation is greater than the preset correlation, constructing a data relationship model between the first test data at every two positions; Using the data monitoring device to monitor second test data at different chip positions of the memory chip; Mapping the second test data to the same data space through the data relationship model to obtain a mapping data set; Calculating the mapping data distance corresponding to the mapping data set; Using the mapping data distance to set second monitoring points at different chip positions of the memory chip; The first monitoring point and the second monitoring point are used as performance monitoring points on the memory chip.

[0008] Optionally, the identifying the data probability distribution of the unstable data includes: Obtaining a minimum value and a maximum value of the unstable data; According to the data minimum value and the data maximum value, a data probability distribution of the unstable data is identified.

[0009] Optionally, performing data smoothing processing on the unstable data by using the data probability distribution to obtain smoothed data includes: Calculating the probability density distribution of the unstable data according to the data probability distribution; Based on the probability density distribution, data smoothing processing is performed on the unstable data to obtain smoothed data.

[0010] Optionally, querying the current scenario corresponding to the performance analysis indicator includes: Identify historical data streams of storage chips; Selecting a data processing indicator for the historical data stream; Obtaining historical analysis indicators of the performance analysis indicators; Analyzing the indicator correlation between the historical analysis indicator and the data processing indicator; Determining a current scenario corresponding to the performance analysis indicator from the historical data stream through the indicator correlation; The data processing indicators include data processing speed and data processing volume.

[0011] Optionally, the analyzing the scene similarity between the current scene and the reference scene includes: Query the current data source, current data target and current execution action of the current scene; Query the comparison data source, comparison data target and comparison execution action of the comparison scenario; Respectively analyzing the source similarity, target similarity, and action similarity between the current data source and the reference data source, the current data target and the reference data target, and the current execution action and the reference execution action; The scene similarity between the current scene and the reference scene is analyzed using the source similarity, the target similarity, and the action similarity.

[0012] Optionally, the calculating the comparison requirement of the comparison scenario for the comparison analysis indicator includes: Get the total scene of the control chip; According to the total scenario, the comparison requirement of the comparison scenario for the comparison analysis indicator is calculated.

[0013] Optionally, analyzing the control performance corresponding to the control indicator includes: Calculating hidden features of the control indicator; According to the hidden feature, the control performance corresponding to the control indicator is analyzed.

[0014] Optionally, the calculating the performance improvement ratio of the current performance relative to the control performance includes: calculating a performance ratio between the current performance and the control performance; The performance ratio is taken as a performance improvement ratio of the current performance relative to the control performance.

[0015] In order to solve the above problems, the present invention also provides a system for intelligently evaluating the performance of a memory chip in a grid array package, the system comprising: A monitoring point determination module, used to determine a performance analysis dimension of a memory chip in a grid array package, select a performance analysis sample of the memory chip based on the performance analysis dimension, apply the performance analysis sample to the memory chip, and determine a performance monitoring point on the memory chip through the performance analysis sample; A data smoothing module, used for collecting the performance monitoring data of the storage chip at the performance monitoring point, dividing the stable data and the unstable data in the performance monitoring data, identifying the data probability distribution of the unstable data, and performing data smoothing processing on the unstable data using the data probability distribution to obtain smoothed data; A scene recognition module, used to use the stable data and the smoothed data as performance analysis indicators of the storage chip, query the current scene corresponding to the performance analysis indicator, obtain a reference chip of the storage chip, and identify a reference scene corresponding to the reference analysis indicator of the reference chip; A demand calculation module, used to analyze the scene similarity between the current scene and the control scene, calculate the control demand of the control scene for the control analysis index, and calculate the current demand of the current scene for the performance analysis index according to the scene similarity and the control demand; a performance analysis module, configured to identify a control index of the control chip from the control analysis indexes using the control requirement, identify a current index of the storage chip from the performance analysis indexes using the current requirement, analyze the control performance corresponding to the control index, and analyze the current performance corresponding to the current index; The performance evaluation module is used to calculate the performance improvement ratio of the current performance relative to the control performance, and use the performance improvement ratio as the performance intelligent evaluation result of the storage chip.

[0016] Compared with the problems described in the background technology, the embodiments of the present invention select unstable data and convert these unstable data into relatively stable data with small fluctuation range based on the probability distribution of unstable data, so that when subsequent data analysis in continuous time periods is performed by LSTM, hidden features of data in continuous time periods can be easily identified. Furthermore, the embodiments of the present invention characterize whether the application scenario requires this performance analysis indicator by calculating the requirement of the scenario for the indicator. If so, it is retained, otherwise it is removed. In this way, when chips suitable for different scenarios are directly compared, the performance of the chip can be correctly judged. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of a flow chart of a method for intelligently evaluating the performance of a memory chip in a grid array package provided by an embodiment of the present invention; Figure 2 A schematic diagram of a module for implementing the intelligent evaluation method for storage chip performance in grid array packaging provided by an embodiment of the present invention.

[0018] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0019] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0020] The embodiment of the present application provides a method for intelligently evaluating the performance of storage chips under grid array packaging. The execution subject of the method for intelligently evaluating the performance of storage chips under grid array packaging includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for intelligently evaluating the performance of storage chips under grid array packaging can be executed by software or hardware installed in a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0021] Embodiment 1: Reference Figure 1 FIG. 1 is a flow chart of a method for intelligently evaluating the performance of a memory chip in a grid array package according to an embodiment of the present invention. In this embodiment, the method for intelligently evaluating the performance of a memory chip in a grid array package includes: S1. Determine a performance analysis dimension of a storage chip under grid array packaging, select a performance analysis sample of the storage chip based on the performance analysis dimension, apply the performance analysis sample to the storage chip, and determine a performance monitoring point on the storage chip through the performance analysis sample.

[0022] In an embodiment of the present invention, the grid array package refers to LGA (Land Grid Array) package. LGA package is an integrated circuit packaging technology. Its principle is to directly connect the solder balls or gold-plated pads of the chip pins to the pads on the printed circuit board (PCB). The memory chip refers to the specific application of the concept of embedded system chip in the storage industry. Whether it is a system chip or a memory chip, it is achieved by embedding software in a single chip to achieve multi-function and high performance, as well as support for multiple protocols, multiple hardware and different applications. Further, the performance analysis dimension refers to the performance basis of the memory chip to be analyzed, which is determined according to the performance analysis requirements. For example, if the performance analysis requirement is the requirement of electrical performance analysis, it is necessary to test the performance analysis dimensions of the memory chip such as voltage and current. If the performance analysis requirement is the requirement of heat dissipation performance analysis, it is necessary to test the performance analysis dimensions of the memory chip such as temperature and heat transfer parameters. The performance analysis sample refers to test data and test software applicable to the memory chip, such as power supply data input into the memory chip, chip test code for testing the data operation status of the memory chip when receiving data to be processed, analyzed and parsed from the outside world, etc.

[0023] In one embodiment of the present invention, determining the performance monitoring point on the memory chip through the performance analysis sample includes: monitoring the first test data at different chip positions of the memory chip using a preset data monitoring device; and calculating the data correlation between the first test data at every two positions in the first test data using the following formula: in, represents the first test data at the first of the two positions, represents the first test data at the second of the two positions, In Indicates the continuous duration is The first position The first test data, Indicates the continuous duration is The second position The first test data, express according to The resulting sequence is arranged, Indicates less than Other moments The number of express The serial number of the performance test data; When the data correlation is not greater than the preset correlation, a first monitoring point is set at different chip positions of the storage chip; when the data correlation is greater than the preset correlation, a data relationship model between the first test data at every two positions is constructed; the data monitoring device is used to monitor the second test data at different chip positions of the storage chip; the second test data is mapped to the same data space through the data relationship model to obtain a mapping data set; and the mapping data distance corresponding to the mapping data set is calculated using the following formula: in, Represents the mapping data distance, Indicates the first numerical values, Indicates the first numerical values, Represents the number of values ​​in the mapped data set; The mapping data distance is used to set second monitoring points at different chip positions of the memory chip; and the first monitoring point and the second monitoring point are used as performance monitoring points on the memory chip.

[0024] Among them, the data monitoring device corresponds to the performance analysis sample. For example, if the performance analysis sample is used to test the current of the storage chip, the data monitoring device is a current sensor. The first test data refers to a continuous data sequence in a continuous time period under multiple chip positions, such as a continuous data sequence at a certain chip position. It should be noted that when the data correlation is not greater than the preset correlation, it means that there are differences between the same type of first test data at different positions. For example, there is a difference in temperature between position 1 and position 3, then it is necessary to set data monitoring devices at position 1 and position 3 respectively. When the data correlation is greater than the preset correlation, for example, it means that the temperature at position 1 is similar to that at position 3, but this is only the temperature similarity within the current continuous time period, and does not mean that the temperature is still similar in the next time period. Therefore, it is necessary to collect data for the next time period, that is, the second test data. The data relationship model represents the functional relationship between the data at each two positions, such as a formula relationship determined by the chip structure, or a relationship determined by a regression model. For example, in the circuit structure, the current flowing through the two branches in the series circuit is related to the two branches. The mapping data set refers to the data on the same chip position calculated by the data relationship model. For example, in the aforementioned trunk and branch, the trunk current remains unchanged and no data mapping is required. The corresponding trunk current is calculated based on the collected current data on the branch using the data relationship model. The second monitoring point refers to when the mapping data distance is greater than a preset distance threshold, indicating that the difference between the data is large, and it is necessary to set up several more data monitoring devices. The mean and variance of the values ​​in the mapping data set can be calculated to select abnormal values, and data monitoring devices are set at the chip positions corresponding to these abnormal values. When the data difference is small, only one chip position corresponding to the first test data is selected to place the data monitoring device. This is because there is a data relationship model between the data at this position and the data at other positions, and the data at other positions can be calculated by the data relationship model, so there is no need to set up data monitoring devices at other positions.

[0025] S2. Collect performance monitoring data of the storage chip at the performance monitoring point, divide the performance monitoring data into stable data and unstable data, identify the data probability distribution of the unstable data, and perform data smoothing on the unstable data using the data probability distribution to obtain smoothed data.

[0026] In the embodiment of the present invention, the stable data refers to data with a small variation range, and the unstable data refers to data with a large variation range. The variance of the data can be calculated and the variance can be used to evaluate the degree of dispersion of the data.

[0027] In one embodiment of the present invention, the identifying the data probability distribution of the unstable data includes: obtaining a data minimum value and a data maximum value of the unstable data; and identifying the data probability distribution of the unstable data using the following formula according to the data minimum value and the data maximum value: in, represents the probability distribution of data, x represents unstable data, a represents the minimum value of data, and b represents the maximum value of data.

[0028] In one embodiment of the present invention, the step of performing data smoothing on the unstable data using the data probability distribution to obtain smoothed data includes: calculating the probability density distribution of the unstable data using the following formula according to the data probability distribution: in, represents the probability density distribution, Represents the probability distribution of the kth unstable data Second power, express Dirichlet distribution , represents the distribution parameter, Indicates the amount of unstable data, represents the gamma function, Indicates the kth unstable data corresponding to ; Based on the probability density distribution, the unstable data is smoothed using the following formula to obtain smoothed data: in, represents smoothed data, represents probability density distribution, and x represents unstable data.

[0029] S3. Use the stable data and the smoothed data as performance analysis indicators of the storage chip, query the current scene corresponding to the performance analysis indicator, obtain a reference chip of the storage chip, and identify a reference scene corresponding to the reference analysis indicator of the reference chip.

[0030] In one embodiment of the present invention, the querying of the current scenario corresponding to the performance analysis indicator includes: identifying the historical data stream of the storage chip; selecting the data processing indicator of the historical data stream; obtaining the historical analysis indicator of the performance analysis indicator; analyzing the indicator correlation between the historical analysis indicator and the data processing indicator; determining the current scenario corresponding to the performance analysis indicator from the historical data stream through the indicator correlation; wherein the data processing indicator includes data processing speed and data processing volume.

[0031] Among them, the historical data stream refers to the product requirements predetermined before creating the storage chip, that is, which business data is specifically processed by creating this new storage chip, and the business data is the historical data stream. The data processing index refers to the data processing speed and the amount of parallel processing of data when using the old chip to process the historical data stream. The historical analysis index refers to the size of the performance analysis index exerted by the old chip in the historical period. The indicator correlation refers to the correlation between two indicator values. The calculation method is similar to the principle of calculating the data correlation between the first test data at every two positions in the first test data mentioned above. The current scene refers to the data stream type when the indicator correlation is greater than the preset correlation, such as digital signals, binary data, image data, etc. Furthermore, the reference chip refers to the old chip, and it is necessary to determine whether it is a chip that lags behind the new chip. The reference scene corresponding to the reference analysis index is similar to the meaning and identification method of the current scene mentioned above, and will not be repeated here.

[0032] S4. Analyze the scene similarity between the current scene and the control scene, calculate the control requirement of the control scene for the control analysis index, and calculate the current requirement of the current scene for the performance analysis index based on the scene similarity and the control requirement.

[0033] In one embodiment of the present invention, the analysis of the scene similarity between the current scene and the control scene includes: querying the current data source, current data target and current execution action of the current scene; querying the control data source, control data target and control execution action of the control scene; respectively analyzing the source similarity, target similarity and action similarity between the current data source and the control data source, the current data target and the control data target, and the current execution action and the control execution action; using the source similarity, target similarity and action similarity to analyze the scene similarity between the current scene and the control scene.

[0034] Optionally, the process of respectively analyzing the source similarity, target similarity, and action similarity between the current data source and the control data source, the current data target and the control data target, and the current execution action and the control execution action refers to the process of analyzing whether the types are similar. For example, when analyzing the source similarity, the source type only needs to be consistent, and it is not necessary for the sources to be exactly the same. For example, if the current data source and the control data source are both image data types, then the current data source is judged to be similar to the control data source, and the similarity judgment between the current data target and the control data target, and the current execution action and the control execution action is similar. It should be noted that the data source refers to the type of data, the data target refers to the data type obtained after a series of processing, and the execution action refers to the operation performed on the data, including data storage, addition, subtraction, multiplication, and division. Furthermore, when the source similarity, the target similarity, and the action similarity are all judged to be similar, the scene similarity is also similar, otherwise they are not similar.

[0035] In one embodiment of the present invention, the calculation of the control requirement of the control scenario for the control analysis indicator includes: obtaining the total scenario of the control chip; and calculating the control requirement of the control scenario for the control analysis indicator according to the total scenario using the following formula: in, represents the control requirement, M represents the number of control scenarios, and N represents the total number of scenarios.

[0036] The total scenario refers to all data scenario types, and the control scenario refers to data types only related to the control analysis indicator.

[0037] S5. Use the control requirement to identify the control index of the control chip from the control analysis index, use the current requirement to identify the current index of the storage chip from the performance analysis index, analyze the control performance corresponding to the control index, and analyze the current performance corresponding to the current index.

[0038] In the embodiment of the present invention, the control index refers to a control analysis index when the control demand is greater than a preset demand threshold, and the current index is the same as the control index.

[0039] In one embodiment of the present invention, the analyzing the control performance corresponding to the control indicator includes: calculating the hidden feature of the control indicator using the following formula: in, represents the hidden features of the forward direction, represents the hidden features of the backward direction, Indicates forward network, Reverse network, express The previous round value of express The previous round value of Indicates The comparison index of the wheel, express The cell state in express The cell state in According to the hidden features, the control performance corresponding to the control index is analyzed using the following formula: in, represents the hidden features of the forward direction, represents the hidden features of the backward direction, represents the activation function, represents the weight matrix, Indicates bias.

[0040] It should be noted that the control performance is divided into multiple levels, such as low performance, medium performance, high performance, etc.

[0041] Optionally, the principle of analyzing the current performance corresponding to the current indicator is similar to the principle of analyzing the comparison performance corresponding to the comparison indicator, and is not elaborated here.

[0042] S6. Calculate a performance improvement ratio of the current performance relative to the control performance, and use the performance improvement ratio as a performance intelligent evaluation result of the storage chip.

[0043] In one embodiment of the present invention, the calculation of the performance improvement ratio of the current performance relative to the control performance includes: calculating the performance ratio between the current performance and the control performance; and using the performance ratio as the performance improvement ratio of the current performance relative to the control performance.

[0044] Compared with the problems described in the background technology, the embodiments of the present invention select unstable data and convert these unstable data into relatively stable data with small variation based on the probability distribution of unstable data, so that when subsequent data analysis in continuous time periods is performed by LSTM, hidden features of data in continuous time periods can be easily identified. Furthermore, the embodiments of the present invention characterize whether the application scenario requires this performance analysis indicator by calculating the requirement of the scenario for the indicator. If so, it is retained, otherwise it is removed. In this way, when chips suitable for different scenarios are directly compared, the performance of the chip can be correctly judged.

[0045] Embodiment 2: like Figure 2 The figure shows a functional module diagram of a storage chip performance intelligent evaluation system under a grid array package of the present invention.

[0046] The intelligent performance evaluation system 200 for storage chips in a grid array package of the present invention can be installed in an electronic device. According to the functions to be implemented, the intelligent performance evaluation system for storage chips in a grid array package can include a monitoring point determination module 201, a data smoothing module 202, a scene recognition module 203, a demand calculation module 204, a performance analysis module 205 and a performance evaluation module 206. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, which are stored in the memory of the electronic device.

[0047] In the embodiment of the present invention, the functions of each module / unit are as follows: The monitoring point determination module 201 is used to determine the performance analysis dimension of the memory chip in the grid array package, select the performance analysis sample of the memory chip based on the performance analysis dimension, apply the performance analysis sample to the memory chip, and determine the performance monitoring point on the memory chip through the performance analysis sample; The data smoothing module 202 is used to collect the performance monitoring data of the storage chip at the performance monitoring point, divide the stable data and the unstable data in the performance monitoring data, identify the data probability distribution of the unstable data, and perform data smoothing on the unstable data using the data probability distribution to obtain smoothed data; The scene recognition module 203 is used to use the stable data and the smoothed data as performance analysis indicators of the storage chip, query the current scene corresponding to the performance analysis indicator, obtain the reference chip of the storage chip, and identify the reference scene corresponding to the reference analysis indicator of the reference chip; The demand calculation module 204 is used to analyze the scene similarity between the current scene and the control scene, calculate the control demand of the control scene for the control analysis index, and calculate the current demand of the current scene for the performance analysis index according to the scene similarity and the control demand; The performance analysis module 205 is used to identify the control index of the control chip from the control analysis index using the control demand, identify the current index of the storage chip from the performance analysis index using the current demand, analyze the control performance corresponding to the control index, and analyze the current performance corresponding to the current index; The performance evaluation module 206 is used to calculate the performance improvement ratio of the current performance relative to the control performance, and use the performance improvement ratio as the performance intelligent evaluation result of the storage chip.

[0048] In detail, the modules in the intelligent evaluation system 200 for storage chip performance under grid array packaging in the embodiment of the present invention are used in the same manner as described above. Figure 1 The same technical means are used as the intelligent evaluation method for storage chip performance under grid array packaging described in the previous section and can produce the same technical effects, which will not be repeated here.

[0049] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0050] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for intelligently evaluating the performance of a memory chip in a grid array package, characterized in that: The method comprises: Determine a performance analysis dimension of a memory chip in a grid array package, select a performance analysis sample of the memory chip based on the performance analysis dimension, apply the performance analysis sample to the memory chip, and determine a performance monitoring point on the memory chip through the performance analysis sample; Collecting performance monitoring data of the storage chip at the performance monitoring point, dividing the performance monitoring data into stable data and unstable data, identifying the data probability distribution of the unstable data, and performing data smoothing processing on the unstable data using the data probability distribution to obtain smoothed data; Using the stable data and the smoothed data as performance analysis indicators of the storage chip, querying a current scene corresponding to the performance analysis indicator, acquiring a reference chip of the storage chip, and identifying a reference scene corresponding to the reference analysis indicator of the reference chip; Analyzing the scene similarity between the current scene and the control scene, calculating the control requirement of the control scene for the control analysis indicator, and calculating the current requirement of the current scene for the performance analysis indicator according to the scene similarity and the control requirement; Using the control requirement to identify the control index of the control chip from the control analysis index, using the current requirement to identify the current index of the storage chip from the performance analysis index, analyzing the control performance corresponding to the control index, and analyzing the current performance corresponding to the current index; A performance improvement ratio of the current performance relative to the control performance is calculated, and the performance improvement ratio is used as a performance intelligent evaluation result of the storage chip.

2. The method for intelligently evaluating the performance of a memory chip in a grid array package according to claim 1, wherein: The determining the performance monitoring point on the storage chip through the performance analysis sample includes: Using a preset data monitoring device to monitor first test data at different chip positions of the memory chip; Calculating the data correlation between the first test data at every two positions in the first test data; When the data correlation is not greater than a preset correlation, setting a first monitoring point on different chip positions of the storage chip; When the data correlation is greater than the preset correlation, constructing a data relationship model between the first test data at every two positions; Using the data monitoring device to monitor second test data at different chip positions of the memory chip; Mapping the second test data to the same data space through the data relationship model to obtain a mapping data set; Calculating mapping data corresponding to the mapping data set; Using the mapping data distance to set second monitoring points at different chip positions of the memory chip; The first monitoring point and the second monitoring point are used as performance monitoring points on the memory chip.

3. The method for intelligently evaluating the performance of a memory chip in a grid array package according to claim 1, wherein: The identifying the data probability distribution of the unstable data comprises: Obtaining a minimum value and a maximum value of the unstable data; According to the data minimum value and the data maximum value, a data probability distribution of the unstable data is identified.

4. The method for intelligently evaluating the performance of a memory chip in a grid array package according to claim 1, wherein: The step of performing data smoothing processing on the unstable data by using the data probability distribution to obtain smoothed data includes: Calculating the probability density distribution of the unstable data according to the data probability distribution; Based on the probability density distribution, data smoothing processing is performed on the unstable data to obtain smoothed data.

5. The method for intelligently evaluating the performance of a memory chip in a grid array package according to claim 1, wherein: The querying of the current scenario corresponding to the performance analysis indicator includes: Identify historical data streams of storage chips; Selecting a data processing indicator for the historical data stream; Obtaining historical analysis indicators of the performance analysis indicators; Analyzing the indicator correlation between the historical analysis indicator and the data processing indicator; Determining a current scenario corresponding to the performance analysis indicator from the historical data stream through the indicator correlation; The data processing indicators include data processing speed and data processing volume.

6. The method for intelligently evaluating the performance of a memory chip in a grid array package according to claim 1, wherein: The analyzing the scene similarity between the current scene and the reference scene includes: Query the current data source, current data target and current execution action of the current scene; Query the comparison data source, comparison data target and comparison execution action of the comparison scenario; Respectively analyzing the source similarity, target similarity, and action similarity between the current data source and the reference data source, the current data target and the reference data target, and the current execution action and the reference execution action; The scene similarity between the current scene and the reference scene is analyzed using the source similarity, the target similarity, and the action similarity.

7. The method for intelligently evaluating the performance of a memory chip in a grid array package according to claim 1, wherein: The calculating the comparison requirement of the comparison scenario to the comparison analysis indicator includes: Get the total scene of the control chip; According to the total scenario, the comparison requirement of the comparison scenario for the comparison analysis indicator is calculated.

8. The method for intelligently evaluating the performance of a memory chip in a grid array package according to claim 1, wherein: The analyzing the control performance corresponding to the control index includes: Calculating hidden features of the control indicator; According to the hidden feature, the control performance corresponding to the control indicator is analyzed.

9. The method for intelligently evaluating the performance of a memory chip in a grid array package according to claim 1, wherein: The calculating the performance improvement ratio of the current performance relative to the control performance includes: calculating a performance ratio between the current performance and the control performance; The performance ratio is taken as a performance improvement ratio of the current performance relative to the control performance.

10. A system for intelligently evaluating the performance of a memory chip in a grid array package, characterized in that: The system comprises: A monitoring point determination module, used to determine a performance analysis dimension of a memory chip in a grid array package, select a performance analysis sample of the memory chip based on the performance analysis dimension, apply the performance analysis sample to the memory chip, and determine a performance monitoring point on the memory chip through the performance analysis sample; A data smoothing module, used for collecting the performance monitoring data of the storage chip at the performance monitoring point, dividing the stable data and the unstable data in the performance monitoring data, identifying the data probability distribution of the unstable data, and performing data smoothing processing on the unstable data using the data probability distribution to obtain smoothed data; A scene recognition module, used to use the stable data and the smoothed data as performance analysis indicators of the storage chip, query the current scene corresponding to the performance analysis indicator, obtain a reference chip of the storage chip, and identify a reference scene corresponding to the reference analysis indicator of the reference chip; A demand calculation module, used to analyze the scene similarity between the current scene and the control scene, calculate the control demand of the control scene for the control analysis index, and calculate the current demand of the current scene for the performance analysis index according to the scene similarity and the control demand; a performance analysis module, configured to identify a control index of the control chip from the control analysis indexes using the control requirement, identify a current index of the storage chip from the performance analysis indexes using the current requirement, analyze the control performance corresponding to the control index, and analyze the current performance corresponding to the current index; The performance evaluation module is used to calculate the performance improvement ratio of the current performance relative to the control performance, and use the performance improvement ratio as the performance intelligent evaluation result of the storage chip.

Images