Internet of Things communication chip performance data analysis processing method

Abstract

The invention belongs to the technical field of data analysis, and particularly relates to an Internet of Things communication chip performance data analysis processing method, which comprises the steps of S1, analysis of the transmission performance of an Internet of Things communication chip, S2, acquisition of an analysis result of the transmission performance, S3, failure analysis of the Internet of Things communication chip, and S4, analysis of the failure of the Internet of Things communication chip. S4, identifying each region containing the wedge interference fringes in the fringe picture; and S5, acquiring initial data of the data sources in the steps S1 to S4. According to the invention, an effective data processing tool is adopted, data analysis is carried out on the Internet of Things communication chip on the basis of abundant data sources so as to provide an efficient data analysis scheme for the Internet of Things communication chip, the analysis efficiency is improved, and according to at least one of the first transmission parameter, the second transmission parameter and the third transmission parameter, the data analysis efficiency of the Internet of Things communication chip is improved. The transmission performance between the adjacent chips is analyzed, the performance bottleneck of chip transmission can be effectively analyzed, and an analysis result with high accuracy is obtained.

Description

Technical Field

[0001] The present invention relates to a chip performance data analysis and processing method, and in particular to an Internet of Things communication chip performance data analysis and processing method. Background Art

[0002] With the rapid development of big data and artificial intelligence related technologies, the development of chips is also changing with each passing day, and the performance requirements of chips are getting higher and higher. As an important part of high-performance computing, general-purpose graphics processors have large-scale thread-level parallel processing capabilities, thus having high-performance characteristics. GPGPU was originally used in fields such as graphics and image processing; with the development of GPGPU architecture, its unique parallel computing architecture has enabled it to have powerful computing capabilities, making it the most important computing acceleration component in the field of general computing, especially in the field of high-performance computing.

[0003] In the field of chip design, considering the chip area and manufacturing yield issues, the area of ​​a chip cannot be too large. In order to achieve higher performance, multiple chips are generally connected to form a larger system through interconnection modules. Common chip interconnection protocols include: PCIE, Interlaken, etc.

[0004] In the related art, the cross-chip transmission performance is analyzed only based on the bandwidth matching between the interconnection module and the external module, and the obtained analysis result cannot accurately reflect the cross-chip transmission performance. In view of this, the present invention designs a performance data analysis and processing method for IoT communication chips. Summary of the invention

[0005] The main purpose of the present disclosure is to provide a method for analyzing and processing performance data of an Internet of Things communication chip, so as to effectively solve the problems raised by the inventor in the above-mentioned background technology.

[0006] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0007] A method for analyzing and processing performance data of an Internet of Things communication chip comprises the following steps:

[0008] Step S1: Analyze the transmission performance of the IoT communication chip, obtain the transmission channel between chips, and the transmission channel includes an input section, a physical layer PHY section and an output section, determine the first transmission parameter corresponding to the input section, the second transmission parameter corresponding to the PHY section, and the third transmission parameter corresponding to the output section, and the second transmission parameter includes: the proportion of IDLE data and the proportion of protocol layer packet data;

[0009] Step S2: obtaining an analysis result of the transmission performance, and analyzing the transmission performance between adjacent chips according to at least one of the first transmission parameter, the second transmission parameter, and the third transmission parameter to obtain an analysis result;

[0010] Step S3: Failure analysis of the IoT communication chip, blowing air to the chip to be tested through a cooling device, emitting a detection beam of a first band and a working beam of a second band simultaneously through a light source assembly, using a DMD chip to reflect the working beam to the chip to be tested, and calculating the stripe width value of the wedge-shaped interference stripe in the stripe picture fed back by an image acquisition device through an image processing algorithm. If the stripe width value is greater than a preset width value, it is determined that there is residual glue on the target chip corresponding to the wedge-shaped interference stripe; controlling the DMD chip to reflect the working beam to the target chip alone to carbonize the residual glue on the target chip;

[0011] Step S4: identifying each region containing the wedge-shaped interference fringe in the fringe image, and adjusting the deflection angle of each galvanometer in the DMD chip according to the difference between the center position of the region and the preset center position, so that the center position of the region overlaps with the preset center position;

[0012] Step S5: acquiring initial data of the data sources in steps S1-S4, wherein the multiple data sources are configured to collect signals from the IoT communication chip to obtain initial data, obtaining a target data file corresponding to the target object based on the initial data and according to the target object, and obtaining a data analysis result corresponding to the target object using a data processing tool based on the target data file;

[0013] Step S6: The multiple data sources include a first data source, a second data source and a third data source, wherein the first data source is configured to collect external interface signals of multiple modules in the chip to obtain initial data corresponding to the first data source; the second data source is configured to collect counting results of performance counters of the multiple modules in the chip to obtain initial data corresponding to the second data source, and the third data source is configured to collect internal design signals of the multiple modules in the chip to obtain initial data corresponding to the third data source.

[0014] Preferably, in step S1, the PHY cross section is located between two adjacent chips.

[0015] Preferably, in step S1, the IDLE data ratio is used to characterize the ratio of IDLE data in all data transmitted on the PHY section, and the protocol layer packet data ratio is used to characterize the ratio of protocol layer packet data in all data transmitted on the PHY section.

[0016] Preferably, in step S1, when the proportion of IDLE data is not greater than the first threshold value, and the proportion of protocol layer packet data is not greater than the second threshold value, a first analysis result is obtained, wherein the first analysis result is used to characterize the need to reduce the sending frequency of link layer packets on the PHY section, or to characterize that the statistics of the second transmission parameter are incorrect; when the proportion of IDLE data is not greater than the first threshold value, and the proportion of protocol layer packet data is greater than the second value, and the proportion of protocol layer packet header data is greater than the third value, a second analysis result is obtained, wherein the second analysis result is used to characterize the need to optimize the packetization strategy for the original data input into the input section.

[0017] Preferably, in step S3, an N-type semiconductor layer, a light-emitting layer and a P-type semiconductor layer are sequentially stacked and grown on a gallium arsenide substrate to form an epitaxial wafer of an Internet of Things communication chip.

[0018] Preferably, in step S3, the P-type semiconductor layer is adhered to the temporary substrate via an adhesive layer, and an angle between the second surface of the P-type semiconductor layer facing the temporary substrate and the first surface is within a preset range.

[0019] Preferably, in step S3, after removing the gallium arsenide substrate, the first electrode and the second electrode of each Internet of Things communication chip are prepared on the side of the epitaxial wafer facing away from the temporary substrate, and each Internet of Things communication chip is cut so that the P-type semiconductor layer of each Internet of Things communication chip is attached to the temporary substrate.

[0020] Preferably, in step S6, the multiple modules include at least two of a cache module, an arbitration module, an instruction distribution and operation module, and a task processing and distribution module.

[0021] Preferably, in step S5, a data processing tool is used to obtain a data analysis result corresponding to the target object, including creating a data structure object in the data processing tool based on the target data file, performing a data analysis operation on the data structure object, and obtaining the data analysis result.

[0022] Preferably, in step S5, based on the initial data, a target data file corresponding to the target object is obtained according to the target object, including generating multiple data files based on the initial data, and obtaining the target data file corresponding to the target object based on the multiple data files according to the target object.

[0023] In view of this, compared with the prior art, the beneficial effects of the present invention are:

[0024] (1) In the present application, the transmission channel includes an input section, a PHY section and an output section, and a first transmission parameter corresponding to the input section, a second transmission parameter corresponding to the PHY section, and a third transmission parameter corresponding to the output section are determined. Then, based on at least one of the first transmission parameter, the second transmission parameter and the third transmission parameter, the transmission performance between adjacent chips is analyzed to obtain an analysis result, which can effectively analyze the performance bottleneck of chip transmission and obtain an analysis result with a high accuracy.

[0025] (ii) In the present application, the working light beam is reflected to the entire chip to be tested by the DMD chip to carbonize the glue layer on the IoT communication chip as a whole, and then the wedge-shaped interference fringes formed by the detection light beam on the temporary substrate are photographed. The target chip with residual glue is found through the fringe width value of the wedge-shaped interference fringes, and finally the residual glue on the target chip is selectively irradiated by the DMD chip to ensure its carbonization.

[0026] (III) In the present application, initial data from a variety of data sources are obtained, and the various data sources correspond to an IoT communication chip. Based on the initial data and according to the target object, a target data file corresponding to the target object is obtained. Based on the target data file, a data processing tool is used to obtain a data analysis result corresponding to the target object. By using effective data processing tools, data analysis is performed on the IoT communication chip based on a variety of data sources to provide an efficient data analysis solution for the IoT communication chip, thereby improving analysis efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 The figure is a schematic flow chart of the method for analyzing and processing performance data of an Internet of Things communication chip provided by the present invention;

[0028] Figure 2 Shown is a schematic diagram of an arbitration module;

[0029] Figure 3 Shown is a schematic diagram of the light source assembly. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] See also Figure 1-3 , the present invention provides the following embodiments:

[0032] A method for analyzing and processing performance data of an Internet of Things communication chip comprises the following steps:

[0033] Step S1: Analyze the transmission performance of the IoT communication chip, obtain the transmission channel between chips, and the transmission channel includes an input section, a physical layer PHY section and an output section, determine the first transmission parameter corresponding to the input section, the second transmission parameter corresponding to the PHY section, and the third transmission parameter corresponding to the output section, and the second transmission parameter includes: the proportion of IDLE data and the proportion of protocol layer packet data;

[0034] Step S2: obtaining an analysis result of the transmission performance, and analyzing the transmission performance between adjacent chips according to at least one of the first transmission parameter, the second transmission parameter, and the third transmission parameter to obtain an analysis result;

[0035] Step S3: Failure analysis of the IoT communication chip, blowing air to the chip to be tested through a cooling device, emitting a detection beam of a first band and a working beam of a second band simultaneously through a light source assembly, using a DMD chip to reflect the working beam to the chip to be tested, and calculating the stripe width value of the wedge-shaped interference stripe in the stripe picture fed back by an image acquisition device through an image processing algorithm. If the stripe width value is greater than a preset width value, it is determined that there is residual glue on the target chip corresponding to the wedge-shaped interference stripe; controlling the DMD chip to reflect the working beam to the target chip alone to carbonize the residual glue on the target chip;

[0036] Step S4: identifying each region containing the wedge-shaped interference fringe in the fringe image, and adjusting the deflection angle of each galvanometer in the DMD chip according to the difference between the center position of the region and the preset center position, so that the center position of the region overlaps with the preset center position;

[0037] Step S5: acquiring initial data of the data sources in steps S1-S4, wherein the multiple data sources are configured to collect signals from the IoT communication chip to obtain initial data, obtaining a target data file corresponding to the target object based on the initial data and according to the target object, and obtaining a data analysis result corresponding to the target object using a data processing tool based on the target data file;

[0038] Step S6: The multiple data sources include a first data source, a second data source and a third data source, wherein the first data source is configured to collect external interface signals of multiple modules in the chip to obtain initial data corresponding to the first data source; the second data source is configured to collect counting results of performance counters of the multiple modules in the chip to obtain initial data corresponding to the second data source, and the third data source is configured to collect internal design signals of the multiple modules in the chip to obtain initial data corresponding to the third data source.

[0039] Specifically, in step S1, the PHY cross section is located between two adjacent chips.

[0040] Specifically, in step S1, the IDLE data ratio is used to characterize the ratio of IDLE data in all data transmitted on the PHY section, and the protocol layer packet data ratio is used to characterize the ratio of protocol layer packet data in all data transmitted on the PHY section.

[0041] Specifically, in step S1, when the proportion of IDLE data is not greater than the first threshold value, and the proportion of protocol layer packet data is not greater than the second threshold value, a first analysis result is obtained, wherein the first analysis result is used to characterize the need to reduce the sending frequency of link layer packets on the PHY section, or to characterize that the statistics of the second transmission parameter are incorrect; when the proportion of IDLE data is not greater than the first threshold value, and the proportion of protocol layer packet data is greater than the second value, and the proportion of protocol layer packet header data is greater than the third value, a second analysis result is obtained, wherein the second analysis result is used to characterize the need to optimize the packetization strategy for the original data input into the input section.

[0042] Specifically, in step S3, an N-type semiconductor layer, a light-emitting layer, and a P-type semiconductor layer are sequentially stacked and grown on a gallium arsenide substrate to form an epitaxial wafer of an Internet of Things communication chip.

[0043] Specifically, in step S3, the P-type semiconductor layer is adhered to the temporary substrate via an adhesive layer, and an included angle between the second surface of the P-type semiconductor layer facing the temporary substrate and the first surface is within a preset range.

[0044] Specifically, in step S3, after removing the gallium arsenide substrate, the first electrode and the second electrode of each Internet of Things communication chip are prepared on the side of the epitaxial wafer away from the temporary substrate, and each Internet of Things communication chip is cut so that the P-type semiconductor layer of each Internet of Things communication chip is attached to the temporary substrate.

[0045] Specifically, in step S6, the multiple modules include at least two of a cache module, an arbitration module, an instruction distribution and operation module, and a task processing and distribution module.

[0046] Specifically, in step S5, a data processing tool is used to obtain a data analysis result corresponding to the target object, including creating a data structure object in the data processing tool based on the target data file, performing a data analysis operation on the data structure object, and obtaining a data analysis result.

[0047] Specifically, in step S5, based on the initial data, a target data file corresponding to the target object is obtained according to the target object, including generating multiple data files based on the initial data, and obtaining the target data file corresponding to the target object based on the multiple data files according to the target object.

[0048] The specific implementation of this embodiment is as follows: the transmission channel includes an input section, a PHY section and an output section, and a first transmission parameter corresponding to the input section, a second transmission parameter corresponding to the PHY section, and a third transmission parameter corresponding to the output section are determined, and then the transmission performance between adjacent chips is analyzed according to at least one of the first transmission parameter, the second transmission parameter and the third transmission parameter to obtain an analysis result, which can effectively analyze the performance bottleneck of chip transmission and obtain an analysis result with a high accuracy rate; the DMD chip reflects the working light beam to the entire chip to be tested, so as to carbonize the glue layer on the IoT communication chip as a whole, and then the wedge-tip interference formed by the detection light beam on the temporary substrate is photographed. Stripes, through the stripe width value of the cleavage interference stripes, the target chip with residual glue is found, and finally the residual glue on the target chip is selectively irradiated by the DMD chip to ensure its carbonization; initial data from multiple data sources are obtained, and the multiple data sources correspond to the Internet of Things communication chip, based on the initial data, according to the target object, a target data file corresponding to the target object is obtained, based on the target data file, a data processing tool is used to obtain a data analysis result corresponding to the target object, and by adopting effective data processing tools, on the basis of rich data sources, data analysis is performed on the Internet of Things communication chip to provide an efficient data analysis solution for the Internet of Things communication chip, thereby improving analysis efficiency.

[0049] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0050] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for analyzing and processing performance data of an Internet of Things communication chip, characterized in that: The following steps are involved: Step S1: Analyze the transmission performance of the IoT communication chip, obtain the transmission channel between chips, and the transmission channel includes an input section, a physical layer PHY section and an output section, determine the first transmission parameter corresponding to the input section, the second transmission parameter corresponding to the PHY section, and the third transmission parameter corresponding to the output section, and the second transmission parameter includes: the proportion of IDLE data and the proportion of protocol layer packet data; Step S2: obtaining an analysis result of the transmission performance, and analyzing the transmission performance between adjacent chips according to at least one of the first transmission parameter, the second transmission parameter, and the third transmission parameter to obtain an analysis result; Step S3: Failure analysis of the IoT communication chip, blowing air to the chip to be tested through a cooling device, emitting a detection beam of a first band and a working beam of a second band simultaneously through a light source assembly, using a DMD chip to reflect the working beam to the chip to be tested, and calculating the stripe width value of the wedge-shaped interference stripe in the stripe picture fed back by an image acquisition device through an image processing algorithm. If the stripe width value is greater than a preset width value, it is determined that there is residual glue on the target chip corresponding to the wedge-shaped interference stripe; controlling the DMD chip to reflect the working beam to the target chip alone to carbonize the residual glue on the target chip; Step S4: identifying each region containing the wedge-shaped interference fringe in the fringe image, and adjusting the deflection angle of each galvanometer in the DMD chip according to the difference between the center position of the region and the preset center position, so that the center position of the region overlaps with the preset center position; Step S5: acquiring initial data of the data sources in steps S1-S4, wherein the multiple data sources are configured to collect signals from the IoT communication chip to obtain initial data, obtaining a target data file corresponding to the target object based on the initial data and according to the target object, and obtaining a data analysis result corresponding to the target object using a data processing tool based on the target data file; Step S6: The multiple data sources include a first data source, a second data source and a third data source, wherein the first data source is configured to collect external interface signals of multiple modules in the chip to obtain initial data corresponding to the first data source; the second data source is configured to collect counting results of performance counters of the multiple modules in the chip to obtain initial data corresponding to the second data source, and the third data source is configured to collect internal design signals of the multiple modules in the chip to obtain initial data corresponding to the third data source.

2. The method for analyzing and processing performance data of an Internet of Things communication chip according to claim 1, characterized in that: In the step S1, the PHY cross section is located between two adjacent chips.

3. The method for analyzing and processing performance data of an Internet of Things communication chip according to claim 2, characterized in that: In the step S1, the IDLE data ratio is used to characterize the ratio of the IDLE data in the total data transmitted on the PHY section, and the protocol layer packet data ratio is used to characterize the ratio of the protocol layer packet data in the total data transmitted on the PHY section.

4. The method for analyzing and processing performance data of an Internet of Things communication chip according to claim 3, characterized in that: In the step S1, when the proportion of IDLE data is not greater than the first threshold value, and the proportion of protocol layer packet data is not greater than the second threshold value, a first analysis result is obtained, wherein the first analysis result is used to characterize the need to reduce the sending frequency of link layer packets on the PHY section, or to characterize that the statistics of the second transmission parameter are incorrect; when the proportion of IDLE data is not greater than the first threshold value, and the proportion of protocol layer packet data is greater than the second value, and the proportion of protocol layer packet header data is greater than the third value, a second analysis result is obtained, wherein the second analysis result is used to characterize the need to optimize the packetization strategy for the original data input into the input section.

5. The method for analyzing and processing performance data of an Internet of Things communication chip according to claim 1, characterized in that: In the step S3, an N-type semiconductor layer, a light-emitting layer and a P-type semiconductor layer are sequentially stacked and grown on a gallium arsenide substrate to form an epitaxial wafer of an Internet of Things communication chip.

6. The method for analyzing and processing performance data of an Internet of Things communication chip according to claim 5, characterized in that: In the step S3, the P-type semiconductor layer is adhered to the temporary substrate through the adhesive layer, and the angle between the second surface of the P-type semiconductor layer facing the temporary substrate and the first surface is within a preset range.

7. The method for analyzing and processing performance data of an Internet of Things communication chip according to claim 5, characterized in that: In the step S3, after removing the gallium arsenide substrate, the first electrode and the second electrode of each Internet of Things communication chip are prepared on the side of the epitaxial wafer away from the temporary substrate, and each Internet of Things communication chip is cut so that the P-type semiconductor layer of each Internet of Things communication chip is attached to the temporary substrate.

8. The method for analyzing and processing performance data of an Internet of Things communication chip according to claim 1, characterized in that: In step S6, the multiple modules include at least two of a cache module, an arbitration module, an instruction distribution and operation module, and a task processing and distribution module.

9. The method for analyzing and processing performance data of an Internet of Things communication chip according to claim 8, characterized in that: In step S5, a data processing tool is used to obtain a data analysis result corresponding to the target object, including creating a data structure object in the data processing tool based on the target data file, performing a data analysis operation on the data structure object, and obtaining the data analysis result.

10. The method for analyzing and processing performance data of an Internet of Things communication chip according to claim 9, characterized in that: In step S5, based on the initial data, a target data file corresponding to the target object is obtained according to the target object, including generating multiple data files based on the initial data, and obtaining the target data file corresponding to the target object based on the multiple data files according to the target object.

Images