A method and system for identifying internal temperature anomalies in a chip.

Abstract

This invention discloses a method and system for identifying internal temperature anomalies in a chip. The method includes: acquiring temperature data and chip fault alarm information at various locations; determining abnormal temperature data from the temperature data and obtaining the chip fault range based on the fault alarm information; generating several temperature distribution information based on the temperature data at each location; acquiring a first sub-temperature distribution information corresponding to the chip fault range and a second sub-temperature distribution information corresponding to the abnormal temperature data from the several temperature distribution information; generating a two-dimensional temperature distribution map based on the first and second sub-temperature distribution information; and identifying various temperature anomaly points in the chip based on the two-dimensional temperature distribution map. This invention can improve the accuracy of identifying internal temperature anomalies in chips.

Description

Technical Field

[0001] This invention relates to the field of integrated circuit chip technology, and in particular to a method and system for identifying abnormal internal temperatures of a chip. Background Technology

[0002] With the optimization and improvement of chip packaging technology, it is no longer possible to directly inspect the internal structure of a chip from its external appearance. Furthermore, when a chip overheats due to a fault, the internal heating process cannot be directly examined, making it impossible to pinpoint the hardware heat sources and thus the location of the internal fault. This necessitates replacing the entire chip, resulting in low chip utilization. Therefore, how to detect abnormal temperature points within a chip is a current research focus.

[0003] The traditional method for detecting temperature anomalies inside a chip is to scan the chip with infrared light to obtain a temperature distribution map and then look for temperature anomalies. However, this method results in a large range of temperature anomalies, and the infrared scanning process itself causes the chip to heat up, leading to low accuracy in identifying temperature anomalies inside the chip. Summary of the Invention

[0004] This invention provides a method and system for identifying internal temperature anomalies in chips to solve the above-mentioned technical problems and effectively improve the accuracy of identifying internal temperature anomalies in chips.

[0005] To address the aforementioned technical problems, this invention provides a method for identifying internal temperature anomalies in a chip, comprising:

[0006] Acquire temperature data and chip fault alarm information at various locations;

[0007] Abnormal temperature data is identified from the temperature data, and the range of chip faults is obtained based on the fault alarm information;

[0008] Based on the temperature data at each location point, several temperature distribution information is generated;

[0009] From several temperature distribution information, obtain the first sub-temperature distribution information corresponding to the chip fault range and the second sub-temperature distribution information corresponding to the abnormal temperature data;

[0010] A two-dimensional temperature distribution map is generated based on the first and second sub-temperature distribution information.

[0011] Based on the two-dimensional temperature distribution map, identify the various temperature anomalies in the chip.

[0012] The beneficial effects of this invention are as follows:

[0013] Compared to existing technologies, such as infrared scanning for identifying chip temperature anomalies, which causes the chip to heat up and thus results in lower identification accuracy, this invention generates a two-dimensional temperature distribution map based on a first sub-temperature distribution information corresponding to the chip fault range and a second sub-temperature distribution information corresponding to abnormal temperature data. This allows the two-dimensional temperature distribution map to specifically contain information related to chip anomalies or faults. Therefore, by identifying various temperature anomalies of the chip based on this two-dimensional temperature distribution map, the invention comprehensively considers the temperature distribution of the chip in different temperature distribution information, chip fault range, and abnormal temperature data, and globally considers the possible temperature anomalies of the chip, thereby comprehensively improving the identification accuracy of temperature anomalies inside the chip.

[0014] Furthermore, the step of obtaining the chip fault range based on fault alarm information includes:

[0015] Based on the fault alarm information, the fault type of the chip is obtained;

[0016] Search the preset database for the chip fault structure corresponding to the fault type;

[0017] Determine the structural range of each structure in the chip;

[0018] Within the structural range of each structure in the chip, the structural range corresponding to the chip faulty structure is taken as the chip fault range.

[0019] This invention identifies the fault type corresponding to the fault alarm information and the chip fault structure, thereby determining the chip fault range and improving the accuracy of identifying the chip fault range. Furthermore, it optimizes the range information of the chip temperature anomaly point and improves the accuracy of identifying the chip temperature anomaly point.

[0020] Furthermore, based on the temperature data at each location point, several temperature distribution information is generated, including:

[0021] Obtain the number of location points and the location information of each location point;

[0022] Based on the number of location points and the location information of each location point, several location point groups are generated;

[0023] For each location point group, based on the location information and temperature data of each location point in the location point group, a temperature fitting strategy is used to obtain the fitted temperature data of each location point in order to generate several temperature distribution information.

[0024] This invention generates temperature distribution information by fitting temperature data from different locations, thereby improving the comprehensiveness of temperature distribution information at various locations of the chip and avoiding the problem that a single temperature distribution information cannot characterize the local temperature distribution features of the chip. This improves the accuracy of subsequent screening of temperature data at various locations and enhances the globality of identifying chip temperature distribution information under the condition of temperature data at different locations.

[0025] Furthermore, based on the number of location points and the location information of each location point, several groups of location points are generated, including:

[0026] Determine the center position of the chip;

[0027] The chip is divided into four regions based on the cross-shaped central axis of the chip, and the region to which each location point belongs is determined.

[0028] Based on location information, obtain the orientation information of each location point relative to the center location point;

[0029] Based on the azimuth information of each location point and the region to which each location point belongs, determine the location points that cannot be in the same group; among them, location points belonging to the same region cannot be in the same group.

[0030] Determine the minimum number of position points in each position point group, and based on the minimum number of position points, arrange and combine the position points to obtain several initial position point groups;

[0031] In each initial position point group, delete the initial position point group that contains position points that cannot be in the same group, resulting in several position point groups.

[0032] This invention improves the reliability and accuracy of the fitted temperature data by deleting location point groups that contain locations that are too close together, thus avoiding the limitations of the obtained temperature distribution information and the problem of overly obvious local temperature data.

[0033] Further, acquiring the first sub-temperature distribution information corresponding to the chip fault range and the second sub-temperature distribution information corresponding to the abnormal temperature data includes:

[0034] At each location point, obtain the fault location points included in the chip fault range;

[0035] Based on several temperature distribution information, the temperature data of the fault location point is obtained from the temperature data of each location point to obtain the first sub-temperature distribution information corresponding to the chip fault range.

[0036] In each location point, identify the abnormal location point corresponding to the abnormal temperature data, and obtain the abnormal location information of the abnormal location point from the location information of each location point;

[0037] Based on several temperature distribution information and anomaly location information, a second sub-temperature distribution information corresponding to the abnormal temperature data is obtained.

[0038] This invention obtains first sub-temperature distribution information corresponding to the chip fault range and second sub-temperature distribution information of the location points corresponding to abnormal temperature data, thereby improving the comprehensiveness of the sub-temperature distribution information. Furthermore, the obtained first and second sub-temperature distribution information are highly correlated with chip faults and abnormal temperatures, so that the subsequently obtained two-dimensional temperature distribution map can specifically characterize information related to chip abnormalities or faults, thereby improving the accuracy of identifying temperature anomalies inside the chip.

[0039] Furthermore, for each group of location points, based on the location information and temperature data of each location point in the group, a temperature fitting strategy is used to obtain fitted temperature data for each location point, including:

[0040] Obtain historical temperature distribution information of the chip;

[0041] Based on historical temperature distribution information, the average value of the temperature data difference between adjacent locations is obtained;

[0042] For each location point group, based on the location information of each location point in the location point group, the temperature data of each location point, and the average value of the temperature data difference between each adjacent location point, the initial fitted temperature data of each other location point corresponding to each location point is obtained.

[0043] Based on the temperature data of each location point and the initial fitted temperature data of each other location point corresponding to each location point, the fitted temperature data of each location point is determined.

[0044] This invention obtains the average value of the temperature data difference between adjacent location points based on historical temperature distribution information, and determines the fitted temperature data of other location points corresponding to each location point by obtaining the average value of the temperature data difference between adjacent location points based on historical temperature distribution information, thereby improving the accuracy of determining the fitted temperature data of other location points.

[0045] Further, the step of generating a two-dimensional temperature distribution map based on the first sub-temperature distribution information and the second sub-temperature distribution information includes:

[0046] For each temperature distribution information, target temperature data for each location point is generated based on the average value of the temperature data difference between adjacent locations, the first sub-temperature distribution information, and the second sub-temperature distribution information.

[0047] Based on the location information of each location point, the target temperature data of each location point is distributed and arranged in a two-dimensional space to generate a two-dimensional temperature distribution map.

[0048] In this invention, the first sub-temperature distribution information and the second sub-temperature distribution information are highly correlated with chip faults and abnormal temperatures, so that the two-dimensional temperature distribution map generated based on the first sub-temperature distribution information and the second sub-temperature distribution information can specifically characterize information related to chip abnormalities or faults, thereby improving the accuracy of identifying temperature anomalies inside the chip.

[0049] Furthermore, the step of identifying various temperature anomalies in the chip based on the two-dimensional temperature distribution map includes:

[0050] From the target temperature data at each location point, obtain the initial temperature anomaly point corresponding to the abnormal temperature data;

[0051] In the two-dimensional temperature distribution map, an abnormal temperature region containing each initial temperature anomaly point is identified;

[0052] Based on the target temperature data of each location point in each abnormal temperature region, obtain the temperature gradient change information of each abnormal temperature region;

[0053] Based on the temperature gradient change information of each abnormal temperature region, the location point corresponding to the gradient center point in each abnormal temperature region is determined to identify each temperature abnormal point of the chip.

[0054] This invention is based on a two-dimensional temperature distribution map. By identifying the gradient center point of each abnormal temperature region, it can determine the temperature anomaly point and improve the accuracy of temperature anomaly point identification.

[0055] Further, determining the location point corresponding to the gradient center point in each abnormal temperature region based on the temperature gradient change information of each abnormal temperature region includes:

[0056] Based on the temperature gradient change information of each abnormal temperature region, the temperature decreasing trend line and the temperature increasing trend line of each abnormal temperature region are obtained.

[0057] The intersection point of the temperature decreasing trend line and the temperature increasing trend line is determined as the location point corresponding to the gradient center point in each abnormal temperature region.

[0058] Accordingly, in order to solve the above-mentioned technical problems, the present invention also provides a chip internal temperature anomaly identification system, including: a data acquisition module, a data processing module, a spectrum generation module and an anomaly identification module;

[0059] The data acquisition module is used to acquire temperature data and chip fault alarm information at each location point;

[0060] The data processing module is used to determine abnormal temperature data from the temperature data, and to obtain the chip fault range based on the fault alarm information; based on the temperature data at each location point, it generates several temperature distribution information.

[0061] The map generation module is used to obtain a first sub-temperature distribution information corresponding to the chip fault range and a second sub-temperature distribution information corresponding to the abnormal temperature data from several temperature distribution information; and to generate a two-dimensional temperature distribution map based on the first sub-temperature distribution information and the second sub-temperature distribution information.

[0062] The anomaly identification module is used to identify various temperature anomalies in the chip based on the two-dimensional temperature distribution map. Attached Figure Description

[0063] Figure 1 : A flowchart illustrating an embodiment of a method for identifying internal temperature anomalies in a chip provided by the present invention;

[0064] Figure 2 : A schematic diagram of an embodiment of a chip internal temperature anomaly identification system provided by the present invention. Detailed Implementation

[0065] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0066] The traditional method for detecting temperature anomalies inside a chip is to scan the chip with infrared light to obtain a temperature distribution map and then look for temperature anomalies. However, this method results in a large range of temperature anomalies, and the infrared scanning process itself causes the chip to heat up, leading to low accuracy in identifying temperature anomalies inside the chip.

[0067] Example 1

[0068] To address the aforementioned technical problems, this invention provides a method and system for identifying internal temperature anomalies in chips, thereby effectively improving the accuracy of identifying internal temperature anomalies in chips.

[0069] Please refer to Figure 1 This is a flowchart illustrating one embodiment of a method for identifying abnormal internal temperatures of a chip, provided by an embodiment of the present invention. Figure 1 As shown, the method for identifying abnormal internal temperatures of the chip includes steps 101 to 106, specifically:

[0070] Step 101: Obtain temperature data and chip fault alarm information at each location point;

[0071] Step 102: Identify abnormal temperature data from the temperature data and obtain the chip fault range based on the fault alarm information;

[0072] Step 103: Based on the temperature data at each location point, generate several temperature distribution information sets;

[0073] Step 104: From several temperature distribution information, obtain the first sub-temperature distribution information corresponding to the chip fault range and the second sub-temperature distribution information corresponding to the abnormal temperature data;

[0074] Step 105: Generate a two-dimensional temperature distribution map based on the first sub-temperature distribution information and the second sub-temperature distribution information;

[0075] Step 106: Based on the two-dimensional temperature distribution map, identify the temperature anomalies of the chip.

[0076] Compared to existing technologies, such as infrared scanning for identifying chip temperature anomalies, which causes the chip to heat up and thus results in lower identification accuracy, this invention generates a two-dimensional temperature distribution map based on a first sub-temperature distribution information corresponding to the chip fault range and a second sub-temperature distribution information corresponding to abnormal temperature data. This allows the two-dimensional temperature distribution map to specifically contain information related to chip anomalies or faults. Therefore, by identifying various temperature anomalies of the chip based on this two-dimensional temperature distribution map, the invention comprehensively considers the temperature distribution of the chip in different temperature distribution information, chip fault range, and abnormal temperature data, and globally considers the possible temperature anomalies of the chip, thereby comprehensively improving the identification accuracy of temperature anomalies inside the chip.

[0077] Further, in step 101, when acquiring chip fault alarm information, temperature data transmitted by temperature sensors preset at different locations on the chip are acquired to obtain current temperature data at multiple locations on the chip detected by the sensors. Then, the alarm content corresponding to the chip's alarm information is collected to obtain chip fault alarm information.

[0078] Further, in step 102, obtaining the chip fault range based on the fault alarm information includes:

[0079] Based on the fault alarm information, the fault type of the chip is obtained;

[0080] Search the preset database for the chip fault structure corresponding to the fault type;

[0081] Determine the structural range of each structure in the chip;

[0082] Within the structural range of each structure in the chip, the structural range corresponding to the chip faulty structure is taken as the chip fault range.

[0083] In this embodiment, a preset database stores the chip fault structure corresponding to each fault type; the chip structure is the hardware structure information that makes up the chip; this embodiment presets the structural range corresponding to each structure.

[0084] This invention identifies the fault type corresponding to the fault alarm information and the chip fault structure, thereby determining the chip fault range and improving the accuracy of identifying the chip fault range. Furthermore, it optimizes the range information of the chip temperature anomaly point and improves the accuracy of identifying the chip temperature anomaly point.

[0085] Furthermore, in step 102, the abnormal temperature data is temperature data that is greater than a preset temperature threshold.

[0086] Further, in step 103, the generation of several temperature distribution information based on the temperature data at each location point includes:

[0087] Obtain the number of location points and the location information of each location point;

[0088] Based on the number of location points and the location information of each location point, several location point groups are generated;

[0089] For each location point group, based on the location information and temperature data of each location point in the location point group, a temperature fitting strategy is used to obtain the fitted temperature data of each location point in order to generate several temperature distribution information.

[0090] This embodiment generates several location point groups based on the number of location points and their location information. For example, if the location points include a, b, c, d, e, and f, then the location point groups include: 1. a, b; 2. a, b, c; 3. a, b, c, d; 4. a, b, c, d, e; 5. a, c; 6. a, d…; na, b, c, d, e, f. Here, each location point group is a combination of the location points arranged in a number greater than the minimum number of location points.

[0091] In this embodiment, the fitted temperature data of all locations are used as the temperature distribution information of the chip.

[0092] This invention generates temperature distribution information by fitting temperature data from different locations, thereby improving the comprehensiveness of temperature distribution information at various locations of the chip and avoiding the problem that a single temperature distribution information cannot characterize the local temperature distribution features of the chip. This improves the accuracy of subsequent screening of temperature data at various locations and enhances the globality of identifying chip temperature distribution information under the condition of temperature data at different locations.

[0093] Furthermore, based on the number of location points and the location information of each location point, several groups of location points are generated, including:

[0094] Determine the center position of the chip;

[0095] The chip is divided into four regions based on the cross-shaped central axis of the chip, and the region to which each location point belongs is determined.

[0096] Based on location information, obtain the orientation information of each location point relative to the center location point;

[0097] Based on the azimuth information of each location point and the region to which each location point belongs, determine the location points that cannot be in the same group; among them, location points belonging to the same region cannot be in the same group.

[0098] Determine the minimum number of position points in each position point group, and based on the minimum number of position points, arrange and combine the position points to obtain several initial position point groups;

[0099] In each initial position point group, delete the initial position point group that contains position points that cannot be in the same group, resulting in several position point groups.

[0100] This invention improves the reliability and accuracy of the fitted temperature data by deleting location point groups that contain locations that are too close together, thus avoiding the limitations of the obtained temperature distribution information and the problem of overly obvious local temperature data.

[0101] Further, in step 104, acquiring the first sub-temperature distribution information corresponding to the chip fault range and the second sub-temperature distribution information corresponding to the abnormal temperature data includes:

[0102] For each temperature distribution information, the fault location points included in the chip fault range are obtained at each location point;

[0103] Based on several temperature distribution information, the temperature data of the fault location point is obtained from the temperature data of each location point to obtain the first sub-temperature distribution information corresponding to the chip fault range.

[0104] In each location point, identify the abnormal location point corresponding to the abnormal temperature data, and obtain the abnormal location information of the abnormal location point from the location information of each location point;

[0105] Based on several temperature distribution information and anomaly location information, a second sub-temperature distribution information corresponding to the abnormal temperature data is obtained.

[0106] This invention obtains first sub-temperature distribution information corresponding to the chip fault range and second sub-temperature distribution information of the location points corresponding to abnormal temperature data, thereby improving the comprehensiveness of the sub-temperature distribution information. Furthermore, the obtained first and second sub-temperature distribution information are highly correlated with chip faults and abnormal temperatures, so that the subsequently obtained two-dimensional temperature distribution map can specifically characterize information related to chip abnormalities or faults, thereby improving the accuracy of identifying temperature anomalies inside the chip.

[0107] Furthermore, for each group of location points, based on the location information and temperature data of each location point in the group, a temperature fitting strategy is used to obtain fitted temperature data for each location point, including:

[0108] Obtain historical temperature distribution information of the chip;

[0109] Based on historical temperature distribution information, the average value of the temperature data difference between adjacent locations is obtained;

[0110] For each location point group, based on the location information of each location point in the location point group, the temperature data of each location point, and the average value of the temperature data difference between each adjacent location point, the initial fitted temperature data of each other location point corresponding to each location point is obtained.

[0111] Based on the temperature data of each location point and the initial fitted temperature data of each other location point corresponding to each location point, the fitted temperature data of each location point is determined.

[0112] In this embodiment, the average value of the temperature data difference between adjacent locations is obtained by identifying the temperature data difference between adjacent locations in the historical temperature distribution information and based on the temperature data difference between adjacent locations corresponding to different historical temperature distribution information.

[0113] This invention obtains the average value of the temperature data difference between adjacent location points based on historical temperature distribution information, and determines the fitted temperature data of other location points corresponding to each location point by obtaining the average value of the temperature data difference between adjacent location points based on historical temperature distribution information, thereby improving the accuracy of determining the fitted temperature data of other location points.

[0114] Further, in step 105, generating a two-dimensional temperature distribution map based on the first sub-temperature distribution information and the second sub-temperature distribution information includes:

[0115] For each temperature distribution information, target temperature data for each location point is generated based on the average value of the temperature data difference between adjacent locations, the first sub-temperature distribution information, and the second sub-temperature distribution information.

[0116] Based on the location information of each location point, the target temperature data of each location point is distributed and arranged in a two-dimensional space to generate a two-dimensional temperature distribution map.

[0117] In this embodiment, for each temperature distribution information, one implementation method for generating target temperature data for each location point based on the average value of the temperature data difference between adjacent location points, the first sub-temperature distribution information, and the second sub-temperature distribution information is as follows: For each temperature distribution information, candidate target temperature data for each location point is generated based on the average value of the temperature data difference between adjacent location points, the first sub-temperature distribution information corresponding to the temperature distribution information, and the second sub-temperature distribution information corresponding to the temperature distribution information; based on the candidate target temperature data for each location point corresponding to each temperature distribution information, the target temperature data for each location point is obtained; specifically, the method for generating candidate target temperature data for each location point is to perform fitting processing on the temperature data of each location point in each sub-temperature distribution information corresponding to each temperature distribution information to obtain the target temperature data for each location point.

[0118] In this invention, the first sub-temperature distribution information and the second sub-temperature distribution information are highly correlated with chip faults and abnormal temperatures, so that the two-dimensional temperature distribution map generated based on the first sub-temperature distribution information and the second sub-temperature distribution information can specifically characterize information related to chip abnormalities or faults, thereby improving the accuracy of identifying temperature anomalies inside the chip.

[0119] Further, in step 106, identifying various temperature anomalies in the chip based on the two-dimensional temperature distribution map includes:

[0120] From the target temperature data at each location point, obtain the initial temperature anomaly point corresponding to the abnormal temperature data;

[0121] In the two-dimensional temperature distribution map, an abnormal temperature region containing each initial temperature anomaly point is identified;

[0122] Based on the target temperature data of each location point in each abnormal temperature region, obtain the temperature gradient change information of each abnormal temperature region;

[0123] Based on the temperature gradient change information of each abnormal temperature region, the location point corresponding to the gradient center point in each abnormal temperature region is determined to identify each temperature abnormal point of the chip.

[0124] This invention is based on a two-dimensional temperature distribution map. By identifying the gradient center point of each abnormal temperature region, it can determine the temperature anomaly point and improve the accuracy of temperature anomaly point identification.

[0125] Further, determining the location point corresponding to the gradient center point in each abnormal temperature region based on the temperature gradient change information of each abnormal temperature region includes:

[0126] Based on the temperature gradient change information of each abnormal temperature region, the temperature decreasing trend line and the temperature increasing trend line of each abnormal temperature region are obtained.

[0127] The intersection point of the temperature decreasing trend line and the temperature increasing trend line is determined as the location point corresponding to the gradient center point in each abnormal temperature region.

[0128] The chip internal temperature anomaly identification method provided in this invention can be applied to application environments where abnormal internal temperature points of IoT chips are identified. This chip internal temperature anomaly identification method can be applied to terminals, servers, or systems including both terminals and servers, and is implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, etc.

[0129] Accordingly, to address the aforementioned technical problems, embodiments of the present invention also provide a chip internal temperature anomaly identification system. Please refer to... Figure 2 This is a schematic diagram of an embodiment of a chip internal temperature anomaly identification system provided by the present invention.

[0130] like Figure 2 As shown, the chip internal temperature anomaly identification system 20 includes: a data acquisition module 201, a data processing module 202, a map generation module 203, and an anomaly identification module 204;

[0131] The data acquisition module 201 is used to acquire temperature data and chip fault alarm information at each location point;

[0132] The data processing module 202 is used to determine abnormal temperature data from the temperature data, and to obtain the chip fault range based on the fault alarm information; and to generate several temperature distribution information based on the temperature data at each location point.

[0133] The map generation module 203 is used to obtain, from several temperature distribution information, a first sub-temperature distribution information corresponding to the chip fault range and a second sub-temperature distribution information corresponding to the abnormal temperature data; and to generate a two-dimensional temperature distribution map based on the first sub-temperature distribution information and the second sub-temperature distribution information.

[0134] The anomaly identification module 204 is used to identify each temperature anomaly point of the chip based on the two-dimensional temperature distribution map.

[0135] The modules in the chip internal temperature anomaly identification system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0136] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0137] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0138] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0139] This invention obtains the chip fault range through chip fault alarm information, thereby optimizing the identification of the range of chip temperature anomalies and improving the accuracy of temperature anomaly identification. By generating multiple temperature distribution information from temperature data at various locations, it improves the globality of chip temperature distribution information identification under different temperature data conditions, avoiding the problem that a single temperature distribution information cannot characterize the local temperature distribution features of the chip. Then, this invention filters the first sub-temperature distribution information corresponding to the fault range and the second sub-temperature distribution information of the abnormal temperature data from several temperature distribution information, which not only improves the targeting of temperature distribution information for identifying the fault range but also enhances the global consideration of other possible temperature anomalies on the chip. Finally, a two-dimensional temperature distribution map of the chip is generated based on multiple sub-temperature distribution information, and each temperature anomaly of the chip is identified based on the two-dimensional temperature distribution map. Thus, it comprehensively considers the temperature distribution of the chip in different temperature distribution information, chip fault ranges, and abnormal temperature data, thereby comprehensively improving the accuracy of identifying internal temperature anomalies of the chip.

[0140] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. It should be understood that although the steps in the flowcharts involved in the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts involved in the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the steps or stages in other steps. In particular, for those skilled in the art, any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for identifying abnormal internal temperature of a chip, characterized in that, include: Acquire temperature data and chip fault alarm information at various locations; Abnormal temperature data is identified from the temperature data, and the range of chip faults is obtained based on the fault alarm information; Based on the temperature data at each location point, several temperature distribution information is generated. Specifically, the number of location points and the location information of each location point are obtained. Based on the number of location points and the location information of each location point, several location point groups are generated. For each location point group, based on the location information and temperature data of each location point in the location point group, the fitted temperature data of each location point is obtained through a temperature fitting strategy to generate several temperature distribution information. From several temperature distribution information, a first sub-temperature distribution information corresponding to the chip fault range and a second sub-temperature distribution information corresponding to the abnormal temperature data are obtained; wherein, at each location point, the fault location point included in the chip fault range is obtained; based on several temperature distribution information, the temperature data of the fault location point is obtained from the temperature data of each location point to obtain the first sub-temperature distribution information corresponding to the chip fault range; at each location point, the abnormal location point corresponding to the abnormal temperature data is determined, and the abnormal point location information of the abnormal location point is obtained from the location information of each location point; based on several temperature distribution information and the abnormal point location information, the second sub-temperature distribution information corresponding to the abnormal temperature data is obtained; A two-dimensional temperature distribution map is generated based on the first and second sub-temperature distribution information. Based on the two-dimensional temperature distribution map, identify the various temperature anomalies in the chip.

2. The method for identifying abnormal internal temperature of a chip as described in claim 1, characterized in that, The process of obtaining the chip fault range based on fault alarm information includes: Based on the fault alarm information, the fault type of the chip is obtained; Search the preset database for the chip fault structure corresponding to the fault type; Determine the structural range of each structure in the chip; Within the structural range of each structure in the chip, the structural range corresponding to the chip faulty structure is taken as the chip fault range.

3. The method for identifying abnormal internal temperature of a chip as described in claim 1, characterized in that, Based on the number of location points and the location information of each location point, several groups of location points are generated, including: Determine the center position of the chip; The chip is divided into four regions based on the cross-shaped central axis of the chip, and the region to which each location point belongs is determined. Based on location information, obtain the orientation information of each location point relative to the center location point; Based on the azimuth information of each location point and the region to which each location point belongs, determine the location points that cannot be in the same group; among them, location points belonging to the same region cannot be in the same group. Determine the minimum number of position points in each position point group, and based on the minimum number of position points, arrange and combine the position points to obtain several initial position point groups; In each initial position point group, delete the initial position point group that contains position points that cannot be in the same group, resulting in several position point groups.

4. The method for identifying abnormal internal temperature of a chip as described in claim 1, characterized in that, For each group of location points, based on the location information and temperature data of each location point in the group, a temperature fitting strategy is used to obtain the fitted temperature data for each location point, including: Obtain historical temperature distribution information of the chip; Based on historical temperature distribution information, the average value of the temperature data difference between adjacent locations is obtained; For each location point group, based on the location information of each location point in the location point group, the temperature data of each location point, and the average value of the temperature data difference between each adjacent location point, the initial fitted temperature data of each other location point corresponding to each location point is obtained. Based on the temperature data of each location point and the initial fitted temperature data of each other location point corresponding to each location point, the fitted temperature data of each location point is determined.

5. The method for identifying abnormal internal temperature of a chip as described in claim 4, characterized in that, The process of generating a two-dimensional temperature distribution map based on the first and second sub-temperature distribution information includes: For each temperature distribution information, target temperature data for each location point is generated based on the average value of the temperature data difference between adjacent locations, the first sub-temperature distribution information, and the second sub-temperature distribution information. Based on the location information of each location point, the target temperature data of each location point is distributed and arranged in a two-dimensional space to generate a two-dimensional temperature distribution map.

6. The method for identifying abnormal internal temperature of a chip as described in claim 5, characterized in that, The process of identifying temperature anomalies in the chip based on the two-dimensional temperature distribution map includes: From the target temperature data at each location point, obtain the initial temperature anomaly point corresponding to the abnormal temperature data; In the two-dimensional temperature distribution map, an abnormal temperature region containing each initial temperature anomaly point is identified; Based on the target temperature data of each location point in each abnormal temperature region, obtain the temperature gradient change information of each abnormal temperature region; Based on the temperature gradient change information of each abnormal temperature region, the location point corresponding to the gradient center point in each abnormal temperature region is determined to identify each temperature abnormal point of the chip.

7. The method for identifying abnormal internal temperature of a chip as described in claim 6, characterized in that, The step of determining the location point corresponding to the gradient center point in each abnormal temperature region based on the temperature gradient change information of each abnormal temperature region includes: Based on the temperature gradient change information of each abnormal temperature region, the temperature decreasing trend line and the temperature increasing trend line of each abnormal temperature region are obtained. The intersection point of the temperature decreasing trend line and the temperature increasing trend line is determined as the location point corresponding to the gradient center point in each abnormal temperature region.

8. A chip internal temperature anomaly identification system, characterized in that, include: Data acquisition module, data processing module, map generation module, and anomaly detection module; The data acquisition module is used to acquire temperature data and chip fault alarm information at each location point; The data processing module is used to determine abnormal temperature data from the temperature data and obtain the chip fault range based on the fault alarm information; it generates several temperature distribution information based on the temperature data of each location point; wherein, it obtains the number of location points and the location information of each location point; it generates several location point groups based on the number of location points and the location information of each location point; for each location point group, it obtains the fitted temperature data of each location point through a temperature fitting strategy based on the location information and temperature data of each location point in the location point group, so as to generate several temperature distribution information. The temperature distribution generation module is used to obtain, from several temperature distribution information, a first sub-temperature distribution information corresponding to the chip fault range and a second sub-temperature distribution information corresponding to abnormal temperature data; and to generate a two-dimensional temperature distribution map based on the first and second sub-temperature distribution information. Specifically, at each location point, the fault location point included in the chip fault range is obtained; based on several temperature distribution information, the temperature data of the fault location point is obtained from the temperature data at each location point to obtain the first sub-temperature distribution information corresponding to the chip fault range; at each location point, the abnormal location point corresponding to the abnormal temperature data is determined, and the abnormal point location information of the abnormal location point is obtained from the location information of each location point; and based on several temperature distribution information and the abnormal point location information, the second sub-temperature distribution information corresponding to the abnormal temperature data is obtained. The anomaly identification module is used to identify various temperature anomalies in the chip based on the two-dimensional temperature distribution map.

Images