A detection method, device, electronic device and readable storage medium
Through multiple burn-in and neural network-like model detection, the problem of long detection time in semiconductor integrated circuits is solved, and efficient grain detection is achieved.
Patent Information
- Application Number
- CN202110668651.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-06-16
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2041-06-16
AI Technical Summary
In semiconductor integrated circuit design, when detecting grain effectiveness based on antifuse or fuse, the existing methods have a long detection time, resulting in low detection efficiency.
The target device is burned multiple times and the burned results are input into the trained neural network model for detection. By analyzing the number of unburned bits, it is determined whether the grain is qualified.
This method can save detection time and improve detection efficiency without determining that the grain is qualified after the target device of all bits is burned out.
Smart Images

Figure CN113448599B_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of integrated circuit technology, and in particular, relates to a detection method, device, electronic device and readable storage medium. Background Art
[0002] In semiconductor integrated circuit design, electronic fuses (E-fuses) are widely used because of their multiple uses. For example, electronic fuses can be used in the grains of integrated circuits. The electronic fuses can be fuses and anti-fuses based on metal-oxide-semiconductor (MOS).
[0003] During the die testing process, the effectiveness of the die based on the antifuse or fuse needs to be tested. The die after the antifuse or fuse in all bits is blown within a limited number of programming times can be determined as a qualified die. This method takes a long time to test, and thus has low test efficiency.
[0004] The above background description is intended to provide an overview of the purpose of the present application and should be read in this light and should not be construed as prior art. Summary of the invention
[0005] The embodiments of the present application provide a detection method, device, electronic device and readable storage medium, which aim to solve the problem that the existing detection time is long and the detection efficiency is low.
[0006] In a first aspect, an embodiment of the present application provides a detection method for detecting a die, wherein the die is used in the design of an integrated circuit, wherein the die is a multi-bit storage structure, wherein the storage structure corresponding to each bit includes a target device for repeated programming, wherein the target device is a fuse or an antifuse;
[0007] The method comprises:
[0008] Programming the target device corresponding to the bit in the die N times; wherein N is ≥ 1 and is an integer;
[0009] Get the burning result after N times of burning;
[0010] The burning result is input into a trained neural network model for detection to obtain a detection result. The neural network model is used to detect whether the grain is qualified.
[0011] In one embodiment, the obtaining the burning result after N times of burning includes:
[0012] Detecting the target device that is not burned out in the die after each burning;
[0013] Get the number of bits corresponding to the target device that is not burned after each burning.
[0014] In one embodiment, the inputting of the burning result into a trained neural network model for detection includes: inputting the number of bits corresponding to the target device that has not been burned out N times into the trained neural network model for detection.
[0015] In one embodiment, the trained neural network-like model is a neural network-like model obtained by training a pre-built neural network-like model based on a labeled data set, and the labeled data set is a data set obtained by labeling the first N burning results of multiple collected qualified grains and unqualified grains.
[0016] In one embodiment, the detecting of the target device in the die that is not burned out after each burning includes:
[0017] The data of the bits in the die are read through a read operation, and the target devices in the die that are not burned out after each burning are detected according to the read data.
[0018] In one embodiment, the step of reading the data of the bits in the die through a read operation and detecting the target devices in the die that are not burned out after each burning according to the read data includes:
[0019] The target device is an antifuse, and when the data of a bit in the die is 1 through a read operation, it is determined that the antifuse in the corresponding bit is blown;
[0020] The target device is an anti-fuse, and when the data of a bit in the die is read as 0 through a read operation, it is determined that the anti-fuse in the corresponding bit is not blown.
[0021] In one embodiment, the step of programming the target device corresponding to the bit in the die N times includes:
[0022] By applying a programming control voltage, the target device corresponding to the bit in the die is programmed N times.
[0023] In a second aspect, an embodiment of the present application provides a detection device for detecting a die, wherein the die is used in the design of an integrated circuit, wherein the die is a multi-bit storage structure, wherein the storage structure corresponding to each bit includes a target device for repeated programming, wherein the target device is a fuse or an antifuse;
[0024] The device comprises:
[0025] A burning module, used for burning the target device corresponding to the bit in the die N times; wherein N ≥ 1 and is an integer;
[0026] The acquisition module is used to obtain the burning results after N times of burning;
[0027] The detection module is used to input the burning result into a trained neural network model for detection to obtain a detection result. The neural network model is used to detect whether the grain is qualified.
[0028] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned detection method when executing the computer program.
[0029] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned detection method are implemented.
[0030] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on an electronic device, enables the electronic device to execute the steps of the above-mentioned detection method.
[0031] Compared with the prior art, the embodiments of the present application have the following beneficial effects: the embodiments of the present application can perform N-times burning of the target device corresponding to the bit in the die, the target device being a fuse or an antifuse; wherein N ≥ 1 and is an integer; obtain the burning result after N-times burning; input the burning result into the trained neural network model for detection to obtain the detection result, and the neural network model is used to detect whether the die is qualified. Since the test result can be obtained by detecting whether the die is qualified in the trained neural network model based on the N-times burning result, it is not necessary to burn out the target devices in all the bits before determining whether the die is a qualified die, thereby saving detection time and improving detection efficiency.
[0032] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0034] Figure 1 It is a flow chart of a detection method provided in one embodiment of the present application;
[0035] Figure 2 is a specific flow chart of step S102 provided in an embodiment of the present application;
[0036] Figure 3 It is a structural diagram of a neural network-like model provided in one embodiment of the present application;
[0037] Figure 4 An embodiment of the present application provides a schematic diagram of result prediction based on input and output of a neural network model;
[0038] Figure 5 is a schematic diagram of the structure of a detection device provided in one embodiment of the present application;
[0039] Figure 6 It is a schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0040] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.
[0041] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.
[0042] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0043] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.
[0044] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.
[0045] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.
[0046] The detection method provided in the embodiments of the present application can be applied to electronic devices such as integrated circuit devices, host computers, mobile phones, tablet computers, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), etc. The embodiments of the present application do not impose any restrictions on the specific types of electronic devices.
[0047] In order to illustrate the technical solution described in this application, the following embodiments are used for illustration.
[0048] See also Figure 1 , a detection method provided in an embodiment of the present application is used to detect a die, wherein the die is used in the design of an integrated circuit, wherein the die is a multi-bit storage structure, wherein the storage structure corresponding to each bit includes a target device for repeated programming, wherein the target device is a fuse or an antifuse;
[0049] Step S101, programming the target device corresponding to the bit in the die N times.
[0050] Specifically, wherein N≥1 and is an integer, the crystal grain may include a number of storage bits, and the core component of the storage bit may be an antifuse or a fuse. The antifuse may be a MOS antifuse. The MOS antifuse is compatible with general logic processes, low-cost, and confidential, and is the mainstream of future applications. The MOS antifuse programming mechanism is to induce the breakdown of the source and drain by high voltage to form a conductive path. Usually, in order to ensure the breakdown of the source and drain, multiple writes are used for programming. The fuse is the opposite of the antifuse, and the conductive path is disconnected after the breakdown. Therefore, when the crystal grain needs to be tested, a test instruction can be sent. When the test instruction is received, the antifuse corresponding to the bit in the crystal grain is programmed N times by adding a certain voltage, such as N can be 5.
[0051] In one embodiment, programming the target device corresponding to the bit in the die N times includes: programming the target device corresponding to the bit in the die N times by applying a programming control voltage.
[0052] Specifically, a predetermined programming control voltage may be applied to the die at preset intervals, so that the anti-fuse or fuse corresponding to the bit in the die is programmed N times by applying the predetermined programming control voltage N times.
[0053] Step S102, obtaining the burning result after N times of burning.
[0054] Specifically, during the N-times programming process, the state of the antifuse and / or fuse corresponding to the bit after each programming of the die is obtained, and the state of the antifuse or fuse corresponding to the bit after each programming is used as the programming result. The state of the antifuse and / or fuse includes a blown state and an unburned state.
[0055] In one embodiment, the step of obtaining the burning result after N burnings comprises step S1021 and step S1022:
[0056] Step S1021, detecting the target devices in the die that are not burned out after each burning.
[0057] Specifically, during the N-times burning process, the fuse or anti-fuse in the crystal grain that has not been burned out after each burning is detected. When the voltage is constant, the anti-fuse is broken down to form a path. This state is called the anti-fuse burned out state. A high level can be pre-connected to the first end of the anti-fuse, and a low level (such as grounding) can be pre-connected to the second end. If the anti-fuse is in the burned out state, a path is formed, and the first end will be pulled to a low level. At this time, the corresponding bit stores data "1". When the anti-fuse is not burned out, the first end is still at a high level. At this time, the corresponding bit stores data "0", that is, the open circuit and the path of the anti-fuse are represented and stored by "0" and "1" respectively, so that the data stored in the bit can be directly read, and the anti-fuse in the crystal grain that has not been burned out can be detected.
[0058] In one embodiment, when the voltage is constant, the fuse is broken down to form an open circuit. This state is called a blown fuse state. A high level can be pre-connected to the first end of the fuse, and a low level (such as grounding) can be pre-connected to the second end. When the fuse is in the on state, the first end is a low level. If the fuse is blown, an open circuit is formed, and the first end will become a high level. At this time, the corresponding bit stores data "0". When the fuse is not blown and is still in the connection, the first end is still at a low level. At this time, the corresponding bit stores data "1", that is, the connection and open circuit of the fuse are represented and stored by "1" and "0" respectively, so that the data stored in the bit can be directly read, and the unburned fuse in the grain can be detected.
[0059] In one embodiment, the detecting the target device in the die that is not burned out after each burning comprises: reading data of bits in the die through a read operation, and detecting the target device in the die that is not burned out after each burning according to the read data.
[0060] In one embodiment, the data of the bit in the grain is read through the read operation, and the target device in the grain that has not been burned out after each burning is detected according to the read data, including: the target device is an antifuse, and when the data of the bit in the grain read through the read operation is 1, it is determined that the antifuse in the corresponding bit is burned out; the target device is an antifuse, and when the data of the bit in the grain read through the read operation is 0, it is determined that the antifuse in the corresponding bit is not burned out.
[0061] Specifically, the data of the bit in the die can be directly read through a read operation, and the unburned anti-fuse in the die after each programming is detected according to the read data. If the data of the bit in the die is 0, it is determined that the corresponding anti-fuse is not burned.
[0062] In one embodiment, when the target device is a fuse, the data of the bit in the grain is read through the read operation, and the target device in the grain that has not been burned out after each burning is detected based on the read data, including: when the data of the bit in the grain read through the read operation is 0, it is determined that the fuse in the corresponding bit is burned out; when the data of the bit in the grain read through the read operation is 1, it is determined that the fuse in the corresponding bit is not burned out.
[0063] Step S1022, obtaining the number of bits corresponding to the target device that is not burned out after each burning.
[0064] Specifically, obtaining the number of bits corresponding to the anti-fuses or fuses that are not blown after each burning can be determining the number of bits of the anti-fuses or fuses that are not blown after each burning, and obtaining the number of bits corresponding to the anti-fuses or fuses that are not blown after each burning.
[0065] Step S103, inputting the burning result into the trained neural network model for detection to obtain a detection result, and the neural network model is used to detect whether the die is qualified.
[0066] Specifically, the neural network model is a network model built based on an artificial neural network, such as Figure 3 As shown, it is a schematic diagram of a neural network structure, including an input layer, a hidden layer (i.e., an intermediate layer) and an output layer. Information is input through the input layer, features are extracted through the hidden layer, and finally the results are output through the output layer.
[0067] In one embodiment, the inputting of the burning result into a trained neural network model for detection includes: inputting the number of bits corresponding to the target device that has not been burned out N times into the trained neural network model for detection.
[0068] In one embodiment, the trained neural network-like model is a neural network-like model obtained by training a pre-built neural network-like model based on a labeled data set, and the labeled data set is a data set obtained by labeling the first N burning results of multiple collected qualified grains and unqualified grains.
[0069] Specifically, a neural network model can be constructed based on an artificial neural network in advance, and the neural network model can be trained in advance. Training the neural network model can be to collect complete burning results of a sufficient number of grains, such as selecting burning results of half of qualified grains and half of unqualified grains for training, such as using the first N burning results of several qualified grains and unqualified grains that have been tested as training samples, and marking each training sample as a qualified grain and an unqualified grain (as a marked expected output), and continuously adjusting and optimizing the parameters in the neural network model according to the marked expected output vector, until the error rate between the result output by the neural network model and the marked result is within a preset range, and a trained neural network model is obtained.
[0070] In actual testing, changes in the process will change the difficulty of anti-fuse or fuse blowing, which in turn affects the change in the number of unburned bits after each die burning. The number of unburned bits in the previous N times can be used to predict whether the die is qualified based on the neural network. The number of bits corresponding to the target device that has not been burned in each of the previous N times detected by the current die is input into the trained neural network model for testing, and the output of the neural network model is the test results of qualified and unqualified die.
[0071] In one embodiment, Figure 4 The figure shows a result prediction diagram of the input and output of a neural network model, which may include the number of bits remaining unburned in the previous N times and the output result of the output layer. For example, it can be assumed that after 10 burns, if there are still bits that have not been burned, the grain is judged as a failed grain (i.e., an unqualified grain). If all the bits can be burned in the previous 10 burns, the grain is judged as a qualified grain. Through the neural network model, it can be predicted whether all the bits can be burned in the previous 10 burns based only on the results of the previous N burns. If N is 5, Figure 4 A relationship graph is shown between the number of unburned bits remaining in the first five times and the output result of the output layer predicting whether all bits can be burned in the first ten times of burning. In the graph, the horizontal axis represents the number of burning times, the vertical axis represents the number of unburned bits remaining each time, the solid line represents the number of unburned bits of qualified grains each time of burning, and the dotted line represents the number of unburned bits of the corresponding unqualified grains each time of burning.
[0072] The embodiment of the present application can perform N-times burning of the target device corresponding to the bit in the die, the target device being a fuse or an antifuse; wherein N ≥ 1 and is an integer; obtain the burning result after N-times burning; input the burning result into the trained neural network model for detection to obtain the detection result, and the neural network model is used to detect whether the die is qualified. Since the test result can be obtained by detecting whether the die is qualified in the trained neural network model based on the N-times burning result, it is not necessary to burn out the target devices in all the bits before determining whether the die is a qualified die, thereby saving detection time and improving detection efficiency.
[0073] The present application also provides a detection device for detecting a die, wherein the die is used in the design of an integrated circuit, wherein the die is a multi-bit storage structure, wherein the storage structure corresponding to each bit includes a target device for repeated programming, wherein the target device is a fuse or an antifuse; and is used to execute the steps in the above detection method embodiment. The detection device may be a virtual appliance in an electronic device, which is run by a processor of the electronic device, or may be the electronic device itself.
[0074] like Figure 5 As shown, the detection device 500 provided in the embodiment of the present application includes:
[0075] The programming module 501 is used to program the target device corresponding to the bit in the die N times; wherein N is greater than or equal to 1 and is an integer;
[0076] An acquisition module 502 is used to acquire the burning result after N times of burning;
[0077] The detection module 503 is used to input the burning result into the trained neural network model for detection to obtain the detection result. The neural network model is used to detect whether the die is qualified.
[0078] In one embodiment, the acquisition module includes:
[0079] A detection unit, used for detecting the target device that is not burned out in the die after each burning;
[0080] The acquisition unit is used to acquire the number of bits corresponding to the target device that is not burned out after each burning.
[0081] In one embodiment, the detection module is specifically used to: input the number of bits corresponding to the target device that has not been burned out N times into a trained neural network model for detection to obtain a detection result, and the neural network model is used to detect whether the die is qualified.
[0082] In one embodiment, the trained neural network-like model is a neural network-like model obtained by training a pre-built neural network-like model based on a labeled data set, and the labeled data set is a data set obtained by labeling the first N burning results of multiple collected qualified grains and unqualified grains.
[0083] In one embodiment, the detection unit is specifically used to: read the data of the bits in the die through a read operation, and detect the target devices in the die that are not burned out after each burning according to the read data.
[0084] In one embodiment, the detection unit comprises:
[0085] A first reading subunit, used when the target device is an antifuse, and when the data of a bit in the die read by the read operation is 1, determines that the antifuse in the corresponding bit is blown;
[0086] The second reading subunit is used for determining that the antifuse in the corresponding bit is not blown when the target device is an antifuse and the data of the bit in the die is 0 through the read operation.
[0087] In one embodiment, the programming module is specifically used to program the target device corresponding to the bit in the die N times by applying a programming control voltage.
[0088] The embodiment of the present application can perform N-times burning of the target device corresponding to the bit in the die, the target device being a fuse or an antifuse; wherein N ≥ 1 and is an integer; obtain the burning result after N-times burning; input the burning result into the trained neural network model for detection to obtain the detection result, and the neural network model is used to detect whether the die is qualified. Since the test result can be obtained by detecting whether the die is qualified in the trained neural network model based on the N-times burning result, it is not necessary to burn out the target devices in all the bits before determining whether the die is a qualified die, thereby saving detection time and improving detection efficiency.
[0089] like Figure 6 As shown, an embodiment of the present invention further provides an electronic device 600 including: a processor 601, a memory 602, and a computer program 603 stored in the memory 602 and executable on the processor 601, such as a detection program. When the processor 601 executes the computer program 603, the steps in the above-mentioned detection method embodiments are implemented. When the processor 601 executes the computer program 603, the functions of the modules in the above-mentioned device embodiments are implemented, such as Figure 5 Functions of modules 501 to 503 are shown.
[0090] Exemplarily, the computer program 603 may be divided into one or more modules, which are stored in the memory 602 and executed by the processor 601 to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 603 in the electronic device 600. For example, the computer program 603 may be divided into a burning module, an acquisition module, and a detection module. The specific functions of each module have been described in the above embodiments and will not be repeated here.
[0091] The electronic device 600 may be an integrated circuit device, a host computer, a computer, a notebook, a PDA, a server, or other electronic device. The electronic device may include, but is not limited to, a processor 601 and a memory 602. Those skilled in the art will appreciate that Figure 6 It is only an example of the electronic device 600 and does not constitute a limitation of the electronic device 600. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.
[0092] The processor 601 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0093] The memory 602 may be an internal storage unit of the electronic device 600, such as a hard disk or memory of the electronic device 600. The memory 602 may also be an external storage device of the electronic device 600, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 600. Further, the memory 602 may also include both an internal storage unit of the electronic device 600 and an external storage device. The memory 602 is used to store the computer program and other programs and data required by the electronic device. The memory 602 may also be used to temporarily store data that has been output or is to be output.
[0094] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0095] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0096] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0097] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0098] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0099] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0100] If the integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.
[0101] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A detection method, characterized in that: Used to detect a crystal grain, the crystal grain is used in the design of an integrated circuit, the crystal grain is a multi-bit storage structure, and the storage structure corresponding to each bit includes a target device for repeated burning, and the target device is a fuse or an antifuse; the method includes: Programming the target device corresponding to the bit in the die N times; wherein N is ≥ 1 and is an integer; Obtaining the burning result after N times of burning, including: detecting the target device that is not burned out in the die after each burning; obtaining the number of bits corresponding to the target device that is not burned out after each burning; Inputting the burning result into a trained neural network model for detection to obtain a detection result, wherein the neural network model is used to detect whether the grain is qualified; Among them, the trained neural network-like model is a neural network-like model obtained by training a pre-constructed neural network-like model according to a labeled data set, and the labeled data set is a data set obtained after labeling the first N burning results of multiple collected qualified grains and unqualified grains.
2. The detection method according to claim 1, characterized in that: The step of inputting the burning result into a trained neural network model for detection includes: inputting the number of bits corresponding to the target device that has not been burned out N times into the trained neural network model for detection.
3. The detection method according to claim 1, characterized in that: The detecting of the target device that is not burned out in the die after each burning comprises: The data of the bits in the die are read through a read operation, and the target devices in the die that are not burned out after each burning are detected according to the read data.
4. The detection method according to claim 3, characterized in that: The method of reading the data of the bit in the die through a read operation and detecting the target device in the die that is not burned out after each burning according to the read data includes: The target device is an antifuse, and when the data of a bit in the die is 1 through a read operation, it is determined that the antifuse in the corresponding bit is blown; The target device is an anti-fuse, and when the data of a bit in the die is read as 0 through a read operation, it is determined that the anti-fuse in the corresponding bit is not blown.
5. The detection method according to any one of claims 1 to 4, characterized in that: The step of programming the target device corresponding to the bit in the die N times includes: By applying a programming control voltage, the target device corresponding to the bit in the die is programmed N times.
6. A detection device, characterized in that: Used to detect a crystal grain, the crystal grain is used in the design of an integrated circuit, the crystal grain is a multi-bit storage structure, and the storage structure corresponding to each bit includes a target device for repeated burning, the target device is a fuse or an anti-fuse; The device comprises: A burning module, used for burning the target device corresponding to the bit in the die N times; wherein N ≥ 1 and is an integer; The acquisition module is used to obtain the burning results after N times of burning, including: detecting the target devices that are not burned out in the die after each burning; obtaining the number of bits corresponding to the target devices that are not burned out after each burning; A detection module, used for inputting the burning result into a trained neural network model for detection to obtain a detection result, wherein the neural network model is used for detecting whether the die is qualified; Among them, the trained neural network-like model is a neural network-like model obtained by training a pre-constructed neural network-like model according to a labeled data set, and the labeled data set is a data set obtained after labeling the first N burning results of multiple collected qualified grains and unqualified grains.
7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.
8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.
