Bad wafer recovery method and device and related equipment

By testing and matching the packaging positions of multiple IO protocol controllers of IO core particles in the chip, the recycling and reuse of the core particles is achieved, the chip waste caused by chip manufacturing process deviation is solved, and the chip cost is reduced.

CN120181837APending Publication Date: 2025-06-20HAIGUANG INFORMATION TECH (SUZHOU) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411315200.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-20
Publication Date
2025-06-20

AI Technical Summary

Technical Problem

As the chip manufacturing process enters the nanoprocess, the yield of chip mass production decreases, resulting in inevitable process deviations, dust loss and other factors in the production and manufacturing process of the core particles, resulting in failure to work normally and excessive waste of chips.

Method used

By obtaining a preset chip including at least IO core particles, multiple IO protocol controllers in the IO core particles are tested, their recycling types are determined, and the IO core particles of the corresponding recycling type are packaged according to the packaging position to obtain the recycling chip.

Benefits of technology

This improves the recycling rate of core particles, reduces the cost of chips, and avoids excessive waste of chips.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120181837A_ABST
    Figure CN120181837A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a bad chip recovery method and device and related equipment, and the method comprises the steps: obtaining a preset chip, a chip architecture at least comprises IO core particles, the IO core particles are provided with a plurality of IO protocol controllers of different types, and the plurality of IO protocol controllers of different types share a physical layer, and are used for achieving different IO protocols; wherein, corresponding to the realization of different IO protocols, the IO core particles are provided with different packaging positions in the preset chip; the multiple IO protocol controllers are tested, the recovery types of the IO core particles are determined, and the recovery types correspond to the failure conditions of the multiple IO protocol controllers and are used for indicating the recovery states of the IO core particles; and according to the packaging position, packaging the IO core particles of the corresponding recovery type to obtain a recovery chip. According to the embodiment of the invention, the recycling rate of the core particles can be improved, and the cost of chips is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Embodiments of the present application relate to the field of chip technology, and in particular, to a method and device for recycling defective chips and related equipment thereof. Background Art

[0002] A die is a unit chip that can implement certain functions and contains an interconnection interface. Through packaging technologies such as 2D, 2.5D, and 3D, multiple dies can be packaged to obtain a chiplet, and the dies can be interconnected based on the interconnection interface, thereby forming a chip with expected functions, such as a SOC (System On Chip) chip.

[0003] However, as the chip manufacturing process enters the nanometer process, the yield of mass-produced chips has decreased significantly. This is mainly because during the production and manufacturing process of dies, inevitable process deviations, dust falling, and other factors lead to abnormal operation. To avoid excessive waste of chips, defective dies can be recycled, and defective dies can be screened out through testing means and reused after corresponding processing.

[0004] In this context, how to provide a defective chip recycling solution to improve the recycling utilization rate of dies and reduce the cost of chips has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0005] In view of this, embodiments of the present application provide a method and device for recycling defective chips and related equipment thereof to achieve improving the recycling utilization rate of dies and reducing the cost of chips.

[0006] In a first aspect, embodiments of the present application provide a method for recycling defective chips, including:

[0007] Obtain a preset chip, where the preset chip includes at least an IO die, the IO die has multiple IO protocol controllers of different types, and the multiple IO protocol controllers of different types share a physical layer for implementing different IO protocols; wherein, for the implementation of different IO protocols, the IO die is set at different packaging positions in the preset chip;

[0008] Test the multiple IO protocol controllers to determine the recycling type of the IO die, where the recycling type corresponds to the failure conditions of the multiple IO protocol controllers and is used to indicate the recycling status of the IO die;

[0009] Package the IO die corresponding to the recycling type according to the packaging position to obtain a recycled chip.

[0010] Optionally, the testing the multiple IO protocol controllers to determine the recycling type of the IO die includes:

[0011] Test the multiple IO protocol controllers, and determine defect information in the multiple IO protocol controllers, where the defect information indicates the failure conditions of the multiple IO protocol controllers;

[0012] Determine the recycling type of the IO die according to the defect information.

[0013] Optionally, the IO protocol controller includes a management configuration module and a data processing module, and a first scan chain is provided corresponding to the management configuration module and the data processing module, and the first scan chain is used to perform a scan test on the execution logics of the management configuration module and the data processing module; the management configuration module includes a configuration domain and a core domain, the core domain is used to configure the core functions of the IO protocol controller, and a second scan chain is provided corresponding to the core domain, and the second scan chain is used to perform a scan test on the execution logic of the core domain; the configuration domain is used to configure the communication parameters of the IO protocol controller;

[0014] The testing of the multiple IO protocol controllers specifically means that, for the multiple IO protocol controllers, respectively based on the first scan chain, scan and test the execution logics of the management configuration module and the data processing module; and, based on the second scan chain, scan and test the execution logic of the core domain.

[0015] Optionally, the types of the IO protocol controllers include a first type of IO protocol controller and a second type of IO protocol controller; the first type of IO protocol controller is used to implement a first IO protocol, and the second type of IO protocol controller is used to implement a second IO protocol;

[0016] The defect information includes:

[0017] Multiple of the first type of IO protocol controllers are all effective, and one or more of the second type of IO protocol controllers fail, and the core domains of the management configuration modules in the multiple second type of IO protocol controllers are all effective;

[0018] Or,

[0019] Multiple of the second IO protocol controllers are all effective, and one or more of the first type of IO protocol controllers fail, and the core domains of the management configuration modules in the multiple first type of IO protocol controllers are all effective;

[0020] Or,

[0021] The core domain of the management configuration module of at least one of the multiple first type of IO protocol controllers fails;

[0022] Or,

[0023] The core domain of the management configuration module of at least one second - type IO protocol controller among the multiple second - type IO protocol controllers fails.

[0024] Optionally, the recycling types include a first recyclable state, a second recyclable state, and a non - recyclable state; wherein, the first recyclable state corresponds to the implementation of a first IO protocol, and the second recyclable state corresponds to the implementation of a second IO protocol.

[0025] Determining the recycling type of the IO die according to the defect information includes:

[0026] If the defect information is that multiple first - type IO protocol controllers are all valid, and one or more second - type IO protocol controllers fail, and the core domains of the management configuration modules in the multiple second - type IO protocol controllers are all valid, determine that the IO die is in the first recyclable state.

[0027] If the defect information is that multiple second - type IO protocol controllers are all valid, and one or more first - type IO protocol controllers fail, and the core domains of the management configuration modules in the multiple first - type IO protocol controllers are all valid, determine that the IO die is in the second recyclable state.

[0028] If the defect information is that the core domain of the management configuration module of at least one first - type IO protocol controller among the multiple first - type IO protocol controllers fails; or the core domain of the management configuration module of at least one second - type IO protocol controller among the multiple second - type IO protocol controllers fails, determine that the IO die is in the non - recyclable state.

[0029] Optionally, if the IO die is in the first recyclable state and / or the second recyclable state, then perform encapsulating the IO die of the corresponding recycling type according to the encapsulation position to obtain a recycled chip.

[0030] If the IO die is in the non - recyclable state, then discard the IO die.

[0031] Optionally, the encapsulation positions include a first encapsulation position and a second encapsulation position.

[0032] Encapsulating the IO die of the corresponding recycling type according to the encapsulation position includes:

[0033] When the IO die is in the first recyclable state, encapsulate the IO die at the first encapsulation position.

[0034] When the IO die is in the second recyclable state, encapsulate the IO die at the second encapsulation position.

[0035] Optionally, after encapsulating the IO die corresponding to the recycling type according to the encapsulation position to obtain a recycled chip, the method further includes:

[0036] Initializing the recycled chip, checking the position identifier of the IO die, placing the idle IO protocol controllers in the IO die in a low-power state, turning off their clock signals, and setting the reset signal to an active state; wherein, the position identifier of the IO die is used to mark the usage status of the multiple IO protocol controllers of the IO die.

[0037] In a second aspect, an embodiment of the present application provides a defective chip recycling device, including:

[0038] A chip acquisition unit, configured to acquire a preset chip, where the preset chip includes at least an IO die, the IO die has multiple IO protocol controllers of different types, and the multiple IO protocol controllers of different types share a physical layer for implementing different IO protocols; wherein, corresponding to the implementation of different IO protocols, the IO die is provided with different encapsulation positions in the preset chip;

[0039] A test determination unit, configured to test the multiple IO protocol controllers to determine the recycling type of the IO die, where the recycling type corresponds to the failure conditions of the multiple IO protocol controllers and is used to indicate the recycling status of the IO die;

[0040] A defective chip encapsulation unit, configured to encapsulate the IO die corresponding to the recycling type according to the encapsulation position to obtain a recycled chip.

[0041] Optionally, it further includes:

[0042] An initialization unit, configured to initialize the recycled chip, check the position identifier of the IO die, place the idle IO protocol controllers in the IO die in a low-power state, turn off their clock signals, and set the reset signal to an active state; wherein, the position identifier of the IO die is used to mark the usage status of the multiple IO protocol controllers of the IO die.

[0043] In a third aspect, an embodiment of the present application provides a chip obtained by recycling based on the defective chip recycling method described in the first aspect above.

[0044] In a fourth aspect, an embodiment of the present application provides a computing device including the defective chip recycling device described in the second aspect above.

[0045] In a fifth aspect, an embodiment of the present application provides a storage medium storing one or more computer-executable instructions, which when executed, implement the defective chip recycling method described in the first aspect above.

[0046] In a sixth aspect, an embodiment of the present application provides a computer program product, which is characterized by including one or more computer-executable instructions that, when executed, implement the defective die recovery method described in the first aspect above.

[0047] The defective die recovery method provided by the embodiment of the present application obtains a preset chip including at least an IO die. When there are multiple IO protocol controllers of different types in the IO die and the multiple IO protocol controllers of different types share a physical layer for implementing different IO protocols, the multiple IO protocol controllers can be tested to determine the recovery type of the IO die indicating the recovery status of the IO die corresponding to the failure conditions of the multiple IO protocol controllers, so that based on the defect conditions of the multiple IO protocol controllers, the recovery strategy (i.e., the recovery type) of the IO die is determined, improving the recovery utilization rate of the IO die; and, in the implementation corresponding to different IO protocols, when the IO die is set at different packaging positions in the preset chip, the IO die of the corresponding recovery type can be packaged according to the packaging position to obtain a recovered chip, so that while recovering the IO die with a defective IO protocol controller, a recovered chip with an unaffected function is obtained, reducing the cost of the chip. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0049] Figure 1 It is an optional structural schematic diagram of a chip.

[0050] Figures 2 to 3 It is an optional architecture schematic diagram of a CPU chip composed of multiple dies.

[0051] Figure 4 It is an optional flowchart of the defective die recovery method provided by the embodiment of the present application.

[0052] Figure 5 It is an optional hierarchical structural schematic diagram of the IO protocol provided by the embodiment of the present application.

[0053] Figure 6 It is an optional internal structural schematic diagram of the IO die provided by the embodiment of the present application.

[0054] Figure 7 It is an optional flowchart of step S200 provided by the embodiment of the present application.

[0055] Figure 8 It is a schematic diagram of an internal optional structure of an IO protocol controller provided by an embodiment of the present application.

[0056] Figure 9 It is another optional flowchart of a defective chip recovery method provided by an embodiment of the present application.

[0057] Figure 10 It corresponds to Figure 3 a schematic diagram of the package of the 64-core CPU chip shown.

[0058] Figure 11 It is an optional block diagram of a defective chip recovery device provided by an embodiment of the present application. Detailed implementation manners

[0059] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0060] For ease of understanding the composition of the chip, Figure 1 a schematic diagram of an optional structure of a chip is exemplarily shown. As Figure 1 shown, the chip may include multiple die (exemplarily shown as die 1, die 2, die 3, and die 4 in the figure). Among them, die 1, die 2, die 3, and die 4 may be the same type of die with the same function, or different types of die with different functions. The die 1, die 2, die 3, and die 4 are encapsulated and integrated through a substrate to obtain Figure 1 the chip shown.

[0061] It should be noted that in the chip design stage, the overall architecture of the chip can be decomposed according to different computing units or functional units required for the chip to achieve the expected function, and one or more die corresponding to different computing units or functional units can be designed according to the chip architecture decomposition scheme, and the die are interconnected and packaged together to achieve the expected function of the chip as a whole. Among them, since a die is a unit chip that can implement a certain function and contains an interconnection interface, multiple die that constitute the same computing unit or functional unit can be called a chiplet. The multiple die in the chiplet can be the same or different. And, based on the interconnection and communication between different modules, the die in the same chiplet can also be used to form different chiplets. Moreover, with the continuous development of semiconductor technology, a single die can contain various functional blocks, so as to achieve effects such as computing. Therefore, in certain specific scenarios, the single die can be regarded as a special chiplet.

[0062] In an alternative example, Figure 2 and Figure 3 show schematic diagrams of alternative architectures of different CPU chips composed of multiple die. Figure 2 is CPU chip 1 with 32 cores, Figure 3 is CPU chip 2 with 64 cores.

[0063] As Figure 2 shown, this 32-core CPU chip 1 may include 2 IO die (IO die m1 and IO die m2 respectively) and 2 CPU die (CPU die n1 and CPU die n2 respectively). Among them, the 2 IO die and the 2 CPU die can be regarded as a chipset, such as chipset A. The 2 IO die are responsible for input / output (I / O) tasks; the 2 CPU die are used to implement the 32-core channel of the CPU.

[0064] As Figure 3 shown, this 64-core CPU chip 2 may include 2 IO die (IO die M1 and IO die M2 respectively) and 4 CPU die (CPU die N1, CPU die N2, CPU die N3, and CPU die N4 respectively). Among them, the 2 IO die and the 4 CPU die can be regarded as a chipset, such as chipset B. The 2 IO die are responsible for input / output (I / O) tasks; the 4 CPU die are used to implement the 64-core channel of the CPU.

[0065] It should be further noted that the production and manufacturing of die refer to etching a pre-designed pattern onto a wafer through a lithography machine to obtain multiple identical unit chips. However, due to inevitable process deviations, dust deposition, and other factors during the production and manufacturing of die, defective die that cannot work properly exist among the obtained die. Therefore, in order to avoid chips obtained by packaging defective die from failing to achieve corresponding functions and being discarded, resulting in excessive waste of chips, it is necessary to recycle defective die. Among them, the recycling of defective die refers to screening out defective die during the production and manufacturing process through testing means, and continuing to use the defective chips after corresponding processing.

[0066] As an alternative implementation, defective die recycling can be performed on the computing cores that make up the chip. For example, multiple CPU computing cores (i.e., CPU die) are integrated inside the CPU chip. When some computing cores of the CPU chip are defective, the defective computing cores can be turned off to achieve defective die recycling of the defective die. Moreover, the CPU chip with the defective computing cores turned off can also be recycled and reused as a chip product with reduced performance.

[0067] However, with the improvement of chip manufacturing processes and the increasing demand for input / output (I / O) bandwidth in data execution, the I / O performance of chips has been continuously improving, the I / O design has become increasingly complex, and the probability of defects in I / O and I / O control logic has become higher and higher. As a result, when defects occur in the I / O of dielets and the logic of I / O-related controllers (such as I / O protocol controllers), the recycling of defective dielets cannot be achieved, specifically the recycling of defective I / O dielets, which reduces the recycling utilization rate of dielets. Further, due to the reduction in the recycling utilization rate of dielets, the cost of chips has also increased accordingly, such as the R & D cost, raw material cost, manufacturing cost, etc. of chips.

[0068] In view of this, the embodiments of the present application propose an improved defective chip recycling scheme. Based on the defect conditions of multiple I / O protocol controllers of I / O dielets, the recycling strategy is determined to improve the recycling utilization rate of I / O dielets and reduce the cost of chips. Among them, the I / O dielet is responsible for performing specific I / O operations and is a hardware component at the physical level; the I / O protocol controller is responsible for managing various different hardware interface standards (such as PCI Express, USB, SPI, etc.) and is used to implement different types of I / O protocols. Among them, some I / O protocol controllers can be used in cooperation with system programs.

[0069] Based on the above idea, as an optional implementation, the embodiments of the present application can obtain a preset chip including at least an I / O dielet. When the I / O dielet has multiple I / O protocol controllers of different types and the multiple I / O protocol controllers of different types share the physical layer and are used to implement different I / O protocols, the multiple I / O protocol controllers can be tested to determine the recycling type of the I / O dielet indicating the recycling status of the I / O dielet corresponding to the failure conditions of the multiple I / O protocol controllers, so that the recycling strategy (i.e., the recycling type) of the I / O dielet is determined based on the defect conditions of the multiple I / O protocol controllers, improving the recycling utilization rate of the I / O dielet; and, when implementing corresponding different I / O protocols, when the I / O dielet is set at different packaging positions in the preset chip, the I / O dielet of the corresponding recycling type can be packaged according to the packaging position to obtain a recycled chip, so that while recycling the I / O dielet with a defective I / O protocol controller, a recycled chip with an unaffected function is obtained, reducing the cost of the chip.

[0070] Among them, Figure 4 An optional flowchart of the defective chip recycling method according to the embodiments of the present application is exemplarily shown. As Figure 4 shown, it may include the following steps:

[0071] Step S100, obtain a preset chip.

[0072] Among them, the preset chip refers to a pre-designed chip for implementing a chip with expected functions. The preset chip may at least include IO die. The IO die may have multiple IO protocol controllers of different types, and the multiple IO protocol controllers of different types share a physical layer for implementing different IO protocols. Moreover, based on the different implemented IO protocols, the IO die of different types may be set at different packaging positions in the preset chip architecture.

[0073] It should be noted that the function of the IO die can be realized based on the execution of the IO protocol controller. Therefore, in order to improve the flexibility and efficiency of the system, one or more IO protocol controllers of different types can be integrated in the IO die, and the IO protocol controllers of different types can implement different IO protocols to provide multiple standard IO interfaces, so that the same IO die can interact with external devices of different types and speeds. In addition, when the chip realizes data input and output through the die interconnection interface, it is based on the die interconnection protocol. Among them, the die interconnection protocol can define the hierarchical mechanism for data transmission between interconnected dies. The die interconnection protocol can include, from top to bottom in the die hierarchy: the Transport Layer, the Link Layer, and the Serdes PHY. The Transport Layer, the Link Layer, and the Serdes PHY are circuit modules implemented in the die based on the die interconnection protocol hierarchy for die interconnection; that is to say, the Transport Layer, the Link Layer, and the Serdes PHY can be in the form of circuit modules. For example, the Transport Layer circuit module (referred to as the Transport Layer for short), the Link Layer circuit module (referred to as the Link Layer for short), and the Serdes PHY circuit module (referred to as the Serdes PHY for short). In a possible implementation, the Serdes PHY can be deployed at the interconnection interface of the die as a circuit module in the interconnection interface; the Transport Layer and the Link Layer can be deployed outside the interconnection interface of the die and set as the upper circuit modules of the Serdes PHY. However, in chip design, compared with the design of the Link Layer and the Transport Layer, the implementation of the Serdes PHY usually requires more chip resources. Therefore, in order to save chip resources, a Serdes PHY design that supports multiple protocols can be used, and the Link Layer and the Transport Layer of multiple protocols can be implemented based on the controller at the same time. When the chip is used, the corresponding protocol can be selected according to the application scenario. As Figure 5 shown in the optional structure schematic diagram of the IO protocol hierarchy, the IO protocol hierarchy can include the Transport Layer (such as Figure 5 the Transport Layer 11 of Protocol 1 and the Transport Layer 21 of Protocol 2 in Figure 5 ), the Link Layer (such as

[0074] the Link Layer 12 of Protocol 1 and the Link Layer 22 of Protocol 2 inFigure 6 An exemplary internal structure schematic diagram of the IO die is shown. As Figure 6 shown, the IO die can simultaneously include a PCIe protocol controller and an inter-die interconnect protocol controller. Thus, for each group of high-speed IOs, based on the corresponding protocol controller, the PCIe protocol and the inter-die interconnect protocol can be simultaneously implemented. Moreover, the PCIe protocol controller and the inter-die interconnect protocol controller share the physical layer.

[0075] Step S200: Test multiple IO protocol controllers to determine the recycling type of the IO die.

[0076] Since defective dies can be screened out by testing means, and the IO die has multiple IO protocol controllers of different types, it is possible to determine the recycling type of the IO die by testing multiple IO protocol controllers. Among them, the recycling type of the IO die in the embodiments of the present application can be understood as the recycling strategy corresponding to the defective IO die. For example, defective IO die A can be recycled; or, defective IO die A cannot be recycled. Moreover, based on testing multiple IO protocol controllers, the recycling type of the IO die can correspond to the failure conditions of the multiple IO protocol controllers and is used to indicate the recycling status of the IO die. The failure conditions of the multiple IO protocol controllers refer to the defective IO protocol controllers existing among the multiple IO protocol controllers.

[0077] It can be understood that in the embodiments of the present application, by testing multiple IO protocol controllers to determine the recycling type of the IO die, a corresponding recycling strategy can be obtained based on the defect conditions of the multiple IO protocol controllers, such as the die can be recycled or cannot be recycled, thereby improving the recycling utilization rate of the IO die.

[0078] Step S300: Package the IO die of the corresponding recycling type according to the packaging position to obtain a recycled chip.

[0079] The packaging position in the embodiments of the present application corresponds to the IO protocol implemented by the IO die. For example, packaging position X is used to package the IO die implementing IO protocol 1, and packaging position Y is used to package the IO die implementing IO protocol 2. Therefore, after determining the recycling type of the IO die, the IO die of the corresponding recycling type can be packaged according to the packaging position to obtain a recycled chip, realizing the recycling of defective dies of the IO die. At the same time, based on the reasonably planned packaging position of the die, when recycling defective IO dies to obtain a chip with the expected function, the cost of the chip is also reduced without affecting the expected function of the chip.

[0080] It can be seen that in the embodiments of the present application, by obtaining a preset chip including at least an IO die, when there are multiple IO protocol controllers of different types in the IO die, and the multiple IO protocol controllers of different types share a physical layer for implementing different IO protocols, the multiple IO protocol controllers can be tested to determine the recovery type of the IO die indicating the recovery status of the IO die corresponding to the failure conditions of the multiple IO protocol controllers, so that based on the defect conditions of the multiple IO protocol controllers, the recovery strategy (i.e., the recovery type) of the IO die is determined, improving the recovery utilization rate of the IO die; and, when implementing different IO protocols, in the case where the IO die is set at different packaging positions in the preset chip, the IO die of the corresponding recovery type can be packaged according to the packaging position to obtain a recovered chip, so that while recovering the IO die with a defective IO protocol controller, a recovered chip with an unaffected function is obtained, reducing the cost of the chip.

[0081] In some embodiments, based on multiple IO protocol controllers of different types corresponding to the IO die, Figure 7 An optional flowchart of step S200 is exemplarily shown. As Figure 7 shown, step S200 may specifically include:

[0082] Step S201, test multiple IO protocol controllers and determine defect information among the multiple IO protocol controllers.

[0083] Generally, among the multiple IO protocol controllers of an IO die, each IO protocol controller can work independently and is responsible for a specific type of I / O operation, which isolates the multiple IO protocol controllers from each other and does not affect each other. Therefore, when there are other problems in a certain IO protocol controller except those affecting the core function, it generally only affects the related devices connected to the IO protocol controller and does not affect the entire IO die. Therefore, the multiple IO protocol controllers of the IO die can be tested to determine defect information among the multiple IO protocol controllers, and the defect information indicates the failure conditions of the multiple IO protocol controllers.

[0084] As an optional implementation, to implement the test of the IO protocol controller, Figure 8 An optional internal structure diagram of the IO protocol controller in the embodiments of the present application is exemplarily shown. As Figure 8 shown, the IO protocol controller may include a management configuration module and a data processing module, and a first scan chain is provided corresponding to the management configuration module and the data processing module.

[0085] The management configuration module is responsible for the initialization settings, configuration management, and connection status of the IO protocol controller. The management configuration module obtains the configuration information of the IO protocol controller, such as baud rate, protocol type, etc., through a bus or other dedicated interfaces, and performs configuration management on the IO protocol controller to ensure the correct interaction between the IO protocol controller and other devices.

[0086] The data processing module is used to receive and send data. When data needs to be transmitted, the data processing module encapsulates, decapsulates, constructs, and splits data packets according to a preset protocol stack. For an IO protocol controller with input and output functions, when performing an input operation, the data processing module can receive data from an external device; when performing an output operation, the data processing module can package the data and send it to a specified target.

[0087] The first scan chain is used to perform scan testing on the execution logics of the management configuration module and the data processing module to verify the basic functions of the management configuration module and the data processing module, ensuring that the management configuration module and the data processing module can work properly according to the expected design. For example: the normal interaction between the management configuration module and the data processing module, and the correct response to input instructions and data processing.

[0088] Moreover, to facilitate the accurate determination of defect information in multiple IO protocol controllers, the IO protocol controller of the embodiment of the present application may have a more refined structure. Refer to Figure 8 As shown, the management configuration module of the IO protocol controller in the embodiment of the present application may include a core domain and a configuration domain, and a second scan chain is provided corresponding to the core domain.

[0089] The core domain focuses on the core functions and basic hardware control of the IO protocol controller, and is used to configure the core functions of the IO protocol controller. The core functions include, for example, at least one of a clock signal, a reset logic, and a low-power state of the physical layer.

[0090] The configuration domain focuses on the IO protocol configuration requirements and is used to configure the communication parameters of the IO protocol controller. The communication parameters are parameters that control the communication process between the IO protocol controller and other devices, such as baud rate selection, data line width, interrupt management, error detection and reporting, etc., to support various application scenarios.

[0091] The second scan chain is used to perform scan testing on the execution logic of the core domain to achieve the test of the manufacturing correctness of the execution logic of the core domain.

[0092] Based on the set first scan chain and second scan chain, when testing multiple IO protocol controllers of an IO die, specifically, for the multiple IO protocol controllers of the IO die, the execution logics of the management configuration module and the data processing module are scanned and tested respectively based on the first scan chain; and, the execution logic of the core domain is scanned and tested based on the second scan chain.

[0093] It should be noted that the multiple IO protocol controllers of the IO die share the physical layer, and the core domain in the management configuration module of the IO protocol controller focuses on the core functions of the IO protocol controller. Refer to Figure 8 As shown, the core domains of the management configuration modules of IO protocol controller a and IO protocol controller b share the same physical layer, which is used to configure the clock signal and reset signal of the IO protocol controller, and configure the low-power state of the physical layer through the configuration bus, and the configuration bus is, for example, a serial or parallel data line.

[0094] In addition, the scan chains (such as the first scan chain and the second scan chain) in the embodiments of the present application can be inserted after the functional design of the IO protocol controller is completed, so that the ordinary registers in the IO protocol controller can be replaced with scan flip-flops, and corresponding tests are performed based on the scan chains to effectively screen out defective chips and improve product quality. And, since the core domain of the management configuration module focuses on the core functions of the IO protocol controller, therefore, it is necessary to ensure the normal operation of the core domain. If there is a defect in the core domain of the management configuration module of an IO protocol controller, the IO die to which the IO protocol controller belongs cannot be recycled.

[0095] Step S202, determine the recycling type of the IO die according to the defect information.

[0096] Based on the fact that the recycling type of the IO die corresponds to the failure conditions of multiple IO protocol controllers, and the defect information indicates the failure conditions of the multiple IO protocol controllers of the IO die, the recycling type of the IO die can be determined according to the defect information.

[0097] In some embodiments, the types of IO protocol controllers can include the first type of IO protocol controller and the second type of IO protocol controller. Among them, the first type of IO protocol controller is used to implement the first IO protocol, and the second type of IO protocol controller is used to implement the second IO protocol.

[0098] Thus, based on multiple IO protocol controllers of different types, and the core domain in the management configuration module of the IO protocol controller focuses on the core functions of the IO protocol controller, the defect information obtained by testing multiple IO protocol controllers can include various situations, as follows.

[0099] Case 1: Multiple first - type IO protocol controllers are all valid, and one or more second - type IO protocol controllers are invalid, and the core domains of the management configuration modules in the multiple second - type IO protocol controllers are all valid;

[0100] Case 2: Multiple second - type IO protocol controllers are all valid, and one or more first - type IO protocol controllers are invalid, and the core domains of the management configuration modules in the multiple first - type IO protocol controllers are all valid.

[0101] Case 3: The core domain of the management configuration module of at least one first - type IO protocol controller among the multiple first - type IO protocol controllers fails;

[0102] Case 4: The core domain of the management configuration module of at least one second - type IO protocol controller among the multiple second - type IO protocol controllers fails.

[0103] It can be understood that since the first - type IO protocol controller is used to implement the first IO protocol and the second - type IO protocol controller is used to implement the second IO protocol, when multiple first - type IO protocol controllers in the IO die are all valid, it can be determined that the first - type IO protocol controllers implementing the first IO protocol are reliable and have no defects; when one or more second - type IO protocol controllers are invalid and the core domains of the management configuration modules in the multiple second - type IO protocol controllers are all valid, it can be determined that there are defects in the second - type IO protocol controllers implementing the second IO protocol in the IO die. Similarly, when multiple second - type IO protocol controllers in the IO die are all valid, it can be determined that the second - type IO protocol controllers implementing the second IO protocol are reliable and have no defects; when one or more first - type IO protocol controllers are invalid and the core domains of the management configuration modules in the multiple first - type IO protocol controllers are all valid, it can be determined that there are defects in the first - type IO protocol controllers implementing the first IO protocol in the IO die.

[0104] In some embodiments, corresponding to the content of the defect information of multiple IO protocol controllers, the recycling types of the IO die can include a first recyclable state, a second recyclable state, and a non - recyclable state. Among them, the first recyclable state corresponds to the implementation of the first IO protocol, and the second recyclable state corresponds to the implementation of the second IO protocol.

[0105] Thus, when determining the recycling type of the IO die according to the defect information, if the defect information is Case 1, that is, multiple first - type IO protocol controllers are all valid, and one or more second - type IO protocol controllers are invalid, and the core domains of the management configuration modules in the multiple second - type IO protocol controllers are all valid, then it can be determined that the IO die is in the first recyclable state.

[0106] If the defect information is Case 2, that is, multiple second IO protocol controllers are all valid, and one or more of the first type of IO protocol controllers fail, and the core domains of the management configuration modules in the multiple first type of IO protocol controllers are all valid, then the IO die can be determined to be in the second recyclable state.

[0107] If the defect information is Case 3 or Case 4, that is, the core domain of the management configuration module of at least one first type of IO protocol controller among the multiple first type of IO protocol controllers fails; or the core domain of the management configuration module of at least one second type of IO protocol controller among the multiple second type of IO protocol controllers fails, then the IO die can be determined to be in the non-recyclable state.

[0108] In an optional example, if the IO die is in the first recyclable state and / or the second recyclable state, indicating that the IO die can be recycled and reused, then step S300 can be executed to package the IO die of the corresponding recycling type according to the packaging position to obtain a recycled chip.

[0109] In an optional example, if the IO die is in the non-recyclable state, then the IO die can be discarded.

[0110] It should be noted that to manufacture a chip with the expected function, after determining that an IO die is in the non-recyclable state and discarding it, a new IO die of the same type can be replaced, and step S200 and step S300 can be executed in sequence until a chip with the expected function is obtained.

[0111] In some embodiments, corresponding to the implementation of different IO protocols, the packaging positions in the embodiments of the present application may include a first packaging position and a second packaging position. The first packaging position may be a position for packaging an IO die that implements the first IO protocol, and the second packaging position may be a position for packaging an IO die that implements the second IO protocol.

[0112] Based on different packaging positions and the corresponding relationship between different recyclable states of the IO die and the implemented IO protocols, when packaging the IO die of the corresponding recycling type according to the packaging position, as an optional implementation, when the IO die is in the first recyclable state, the IO die is packaged to the first packaging position. As another optional implementation, when the IO die is in the second recyclable state, the IO die is packaged to the second packaging position.

[0113] It can be understood that since different types of IO protocol controllers can be used to implement different IO protocols in the same IO die, when the IO protocol controllers corresponding to an IO protocol are all effective in the IO die, even if the IO die with defective IO protocol controllers corresponding to the recycling state is packaged at the packaging position, it will not affect the execution of the IO protocol of the same type and effective IO protocol controllers in the IO die, making the function of the finally obtained recycled chip meet the expected requirements.

[0114] In some embodiments, to avoid normal logic execution in the IO die or increase the power consumption of the IO die, Figure 9 An alternative flowchart of the defective die recycling method in the embodiments of the present application is exemplarily shown. As Figure 9 shown, after step S300, step S400 can further be included to initialize the recycled chip and check the position identifier of the IO die.

[0115] Among them, the position identifier of the IO die can be used to mark the usage status of multiple IO protocol controllers of the IO die. By checking the position identifier of the IO die, the idle IO protocol controllers in the IO die can be placed in a low-power state, its clock signal can be turned off, and the reset signal can be placed in an effective state.

[0116] It can be understood that during the power-on process of the chip, by checking the position identifier of the IO die, the usage status of each IO protocol controller in the IO die can be confirmed to ensure correct hardware configuration and optimized resource allocation of the IO die. When an unused idle IO protocol controller is found, the IO protocol controller can be placed in a low-power state, thereby reducing the power consumption of the IO die, turning off the clock signal of the IO protocol controller, and placing the reset signal in an effective state for normal startup and configuration operations.

[0117] To facilitate understanding of the defective die recycling method in the embodiments of the present application, Figure 3 the 64-core CPU chip shown is used as a preset chip for explanation. Among them, both IO die M1 and IO die M2 contain 4 inter-chip interconnect protocol controllers and 4 PCLe protocol controllers, and the 4 inter-chip interconnect protocol controllers and 4 PCLe protocol controllers share the physical layer. The 4 inter-chip interconnect protocol controllers and the physical layer implement 4 groups of inter-chip interconnect protocols, and the 4 PCLe protocol controllers and the physical layer implement 4 groups of PCLe protocols. And, corresponding to Figure 3 the 64-core CPU chip shown, Figure 10 An exemplary packaging schematic diagram of the 64-core CPU chip is shown. As Figure 10As shown, for the implementation of the inter-die interconnect protocol, the setting position of the IO die in the preset chip can be L1; for the implementation of the PCLe protocol, the setting position of the IO die in the preset chip can be L2.

[0118] Each inter-die interconnect protocol controller and PCLe protocol controller is provided with a management configuration module and a data processing module, and a first scan chain is provided corresponding to the management configuration module and the data processing module; the management configuration module is provided with a configuration domain and a core domain, and a second scan chain is provided corresponding to the core domain.

[0119] First, test the 4 inter-die interconnect protocol controllers and 4 PCLe protocol controllers of the IO die M1. Specifically, the execution logic of the management configuration module and the data processing module can be scanned and tested respectively based on the first scan chain, and the execution logic of the core domain can be scanned and tested based on the second scan chain.

[0120] If it is tested that all 4 inter-die interconnect protocol controllers of the IO die M1 are effective and there are no defects, it can be determined that the inter-die interconnect protocol can operate effectively. If one or more of the 4 PCLe protocol controllers fail and the configuration management core domains of the 4 PCLe protocol controllers are all effective, it can be determined that there are defects in the PCLe protocol controllers in the IO die M1, and the operation of the PCLe protocol may malfunction. Therefore, the IO die M1 can be marked as recyclable state 1 to indicate the effective operation of the inter-die interconnect protocol.

[0121] Furthermore, the IO die M1 can be packaged at the L1 position.

[0122] If it is tested that all 4 PCLe protocol controllers of the IO die M1 are effective and there are no defects, it can be determined that the PCLe can operate effectively. If one or more of the 4 inter-die interconnect protocol controllers fail and the configuration management core domains of the 4 inter-die interconnect protocol controllers are all effective, it can be determined that there are defects in the inter-die interconnect protocol controllers in the IO die M1, and the operation of the inter-die interconnect protocol may malfunction. Therefore, the IO die M1 can be marked as recyclable state 2 to indicate the effective operation of the PCLe.

[0123] Furthermore, the IO die M2 can be packaged at the L2 position.

[0124] If it is tested that the configuration management core domain of at least one protocol controller among the 4 inter-die interconnect protocol controllers or 4 PCLe protocol controllers of the IO die M1 fails, the IO die M1 can be marked as non-recyclable. For the non-recyclable IO die M1, it can be discarded and replaced with a new IO die of the same type, such as the IO die M3, and the test steps can be performed on the IO die M3.

[0125] It should be noted that Figure 10 The process of realizing defective die recovery by taking the IO die M2 as an example in Figure 10 can be referred to the above content in the same way, and the embodiments of the present application will not elaborate on this too much.

[0126] By packaging the IO die M1 in the recyclable state 1 at the L1 position, a recovered 64-core CPU chip with the inter-chip interconnect protocol function not affected can be obtained. Furthermore, initialize the 64-core CPU chip, check the position identifier of the IO die M1. If 4 PCIe protocol controllers in the IO die M1 are idle, that is, only 4 inter-chip interconnect protocol controllers in the IO die M1 are used, then place 4 PCIe protocol controllers in the IO die M2 in the low-power state, turn off their clock signals, and place the reset signal in the valid state to avoid normal logic execution in the IO die M1 or increase the power consumption of the IO die.

[0127] It can be seen that in the embodiments of the present application, by obtaining a preset chip including at least an IO die, when the IO die has multiple IO protocol controllers of different types, and the multiple IO protocol controllers of different types share a physical layer for implementing different IO protocols, the multiple IO protocol controllers can be tested to determine the recovery type of the IO die indicating the recovery state of the IO die corresponding to the failure conditions of the multiple IO protocol controllers, so as to determine the recovery strategy (i.e., recovery type) of the IO die based on the defect conditions of the multiple IO protocol controllers, improving the recovery utilization rate of the IO die; and, when implementing corresponding different IO protocols, in the case where the IO die is set at different packaging positions in the preset chip, the IO die of the corresponding recovery type can be packaged according to the packaging position to obtain a recovered chip, so that while recovering the IO die with defective IO protocol controllers, a recovered chip with the function not affected is obtained, reducing the cost of the chip.

[0128] Next, the device for defective die recovery provided by the embodiments of the present application will be introduced. The device content described below can be considered as a chip recovery device or a computing device, which is a functional module required to implement the defective die recovery method provided by the embodiments of the present application. The device content described below can be correspondingly referred to the method content described above.

[0129] Figure 11 The optional block diagram of the defective die recovery device provided by the embodiments of the present application is shown. As Figure 11 shown, the device may include:

[0130] A chip acquisition unit 300 is configured to acquire a preset chip, where the preset chip includes at least an IO die, the IO die has multiple IO protocol controllers of different types, and the multiple IO protocol controllers of different types share a physical layer for implementing different IO protocols; wherein, corresponding to the implementation of different IO protocols, the IO die is set at different packaging positions in the preset chip;

[0131] A test determination unit 310 is configured to test the multiple IO protocol controllers to determine a recovery type of the IO die, where the recovery type corresponds to a failure condition of the multiple IO protocol controllers and is used to indicate a recovery status of the IO die;

[0132] A defective die packaging unit 320 is configured to package the IO die corresponding to the recovery type according to the packaging position to obtain a recovered chip.

[0133] Optionally, when the test determination unit 310 tests the multiple IO protocol controllers to determine the recovery type of the IO die, it includes:

[0134] Testing the multiple IO protocol controllers to determine defect information in the multiple IO protocol controllers, where the defect information indicates a failure condition of the multiple IO protocol controllers;

[0135] Determining the recovery type of the IO die according to the defect information.

[0136] Optionally, the IO protocol controller includes a management configuration module and a data processing module, and a first scan chain is provided corresponding to the management configuration module and the data processing module, where the first scan chain is used to perform a scan test on the execution logics of the management configuration module and the data processing module; the management configuration module includes a configuration domain and a core domain, the core domain is used to configure core functions of the IO protocol controller, and a second scan chain is provided corresponding to the core domain, where the second scan chain is used to perform a scan test on the execution logic of the core domain; the configuration domain is used to configure communication parameters of the IO protocol controller;

[0137] When the test determination unit 310 tests the multiple IO protocol controllers of the IO die, specifically, for the multiple IO protocol controllers, based on the first scan chain, the execution logics of the management configuration module and the data processing module are scanned and tested respectively; and, based on the second scan chain, the execution logic of the core domain is scanned and tested.

[0138] Optionally, the types of the IO protocol controllers include a first type of IO protocol controller and a second type of IO protocol controller; the first type of IO protocol controller is used to implement a first IO protocol, and the second type of IO protocol controller is used to implement a second IO protocol;

[0139] The defect information includes:

[0140] Multiple first - type IO protocol controllers are all valid, and one or more second - type IO protocol controllers are invalid, and the core domains of the management configuration modules in multiple second - type IO protocol controllers are all valid;

[0141] Or,

[0142] Multiple second IO protocol controllers are all valid, and one or more first - type IO protocol controllers are invalid, and the core domains of the management configuration modules in multiple first - type IO protocol controllers are all valid;

[0143] Or,

[0144] The core domain of the management configuration module of at least one first - type IO protocol controller among multiple first - type IO protocol controllers fails;

[0145] Or,

[0146] The core domain of the management configuration module of at least one second - type IO protocol controller among multiple second - type IO protocol controllers fails.

[0147] Optionally, the recycling types include a first recyclable state, a second recyclable state, and a non - recyclable state; wherein, the first recyclable state corresponds to the implementation of the first IO protocol, and the second recyclable state corresponds to the implementation of the second IO protocol;

[0148] The test determination unit 310 determines the recycling type of the IO die according to the defect information, including:

[0149] If the defect information is that multiple first - type IO protocol controllers are all valid, and one or more second - type IO protocol controllers are invalid, and the core domains of the management configuration modules in multiple second - type IO protocol controllers are all valid, determine that the IO die is in the first recyclable state;

[0150] If the defect information is that multiple second IO protocol controllers are all valid, and one or more first - type IO protocol controllers are invalid, and the core domains of the management configuration modules in multiple first - type IO protocol controllers are all valid, determine that the IO die is in the second recyclable state;

[0151] If the defect information is that the core domain of the management configuration module of at least one first - type IO protocol controller among the multiple first - type IO protocol controllers fails; or, the core domain of the management configuration module of at least one second - type IO protocol controller among the multiple second - type IO protocol controllers fails, determine that the IO die is in a non - recyclable state.

[0152] Optionally, if the IO die is in the first recyclable state and / or the second recyclable state, the defective die packaging unit 320 performs the step of packaging the IO die of the corresponding recycling type according to the preset packaging position to obtain a recycled chip.

[0153] If the IO die is in a non - recyclable state, the defective die packaging unit 320 discards the IO die.

[0154] Optionally, the packaging position includes a first packaging position and a second packaging position.

[0155] The step in which the defective die packaging unit 320 packages the IO die of the corresponding recycling type according to the packaging position includes:

[0156] When the IO die is in the first recyclable state, package the IO die to the first packaging position.

[0157] When the IO die is in the second recyclable state, package the IO die to the second packaging position.

[0158] Optionally, the device further includes:

[0159] An initialization unit 330, configured to initialize the recycled chip, check the position identifier of the IO die, place the idle IO protocol controllers in the IO die in a low - power state, turn off their clock signals, and set the reset signal to an active state; wherein, the position identifier of the IO die is used to mark the usage status of the multiple IO protocol controllers of the IO die.

[0160] It can be seen that the defective die recycling device of the embodiments of the present application can determine the recycling strategy (i.e., the recycling type) of the IO die based on the defect conditions of multiple IO protocol controllers, improve the recycling utilization rate of the IO die, and, while recycling the IO die with defective IO protocol controllers, obtain a recycled chip whose function is not affected, reducing the cost of the chip.

[0161] The embodiments of the present application further provide a chip, which is obtained by recycling based on the defective die recycling method provided by the embodiments of the present application.

[0162] The embodiments of the present application further provide a computing device, such as a server device or a terminal device, which may include the defective die recycling device provided by the embodiments of the present application.

[0163] An embodiment of the present application further provides a storage medium storing one or more computer-executable instructions, which, when executed, implement the defective chip recovery method provided by the embodiment of the present application.

[0164] An embodiment of the present application further provides a computer program product including one or more computer-executable instructions, which, when executed, implement the defective chip recovery method provided by the embodiment of the present application.

[0165] The above describes multiple embodiment solutions provided by the embodiments of the present application. The optional ways introduced in each embodiment solution can be combined and cross-referenced with each other without conflict, thereby extending multiple possible embodiment solutions, all of which can be considered as the embodiment solutions disclosed and made public by the embodiments of the present application.

[0166] Although the embodiments of the present application are disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application should be subject to the scope defined by the claims.

Claims

1. A bad chip recycling method, characterized in that: include: Obtain a preset chip, the preset chip at least comprising an IO core particle, the IO core particle having a plurality of IO protocol controllers of different types, and the plurality of IO protocol controllers of different types share a physical layer for implementing different IO protocols; wherein, corresponding to the implementation of different IO protocols, the IO core particles are provided with different packaging positions in the preset chip; Testing the multiple IO protocol controllers to determine a recovery type of the IO core particles, wherein the recovery type corresponds to a failure condition of the multiple IO protocol controllers and is used to indicate a recovery state of the IO core particles; According to the packaging position, IO core particles of corresponding recycling types are packaged to obtain recycled chips.

2. The method according to claim 1, characterized in that The testing of the plurality of IO protocol controllers to determine the recycling type of the IO core particles includes: Testing the plurality of IO protocol controllers, and determining defect information in the plurality of IO protocol controllers, wherein the defect information indicates a failure condition of the plurality of IO protocol controllers; The recycling type of the IO chip is determined according to the defect information.

3. The method according to claim 2, characterized in that The IO protocol controller includes a management configuration module and a data processing module, and a first scan chain is provided corresponding to the management configuration module and the data processing module, and the first scan chain is used to scan and test the execution logic of the management configuration module and the data processing module; the management configuration module includes a configuration domain and a core domain, the core domain is used to configure the core function of the IO protocol controller, and a second scan chain is provided corresponding to the core domain, and the second scan chain is used to scan and test the execution logic of the core domain; the configuration domain is used to configure the communication parameters of the IO protocol controller; The testing of the multiple IO protocol controllers is specifically: for the multiple IO protocol controllers, based on the first scan chain, respectively, scanning and testing the execution logic of the management configuration module and the data processing module; and based on the second scan chain, scanning and testing the execution logic of the core domain.

4. The method according to claim 3, characterized in that The types of the IO protocol controllers include a first type of IO protocol controller and a second type of IO protocol controller; the first type of IO protocol controller is used to implement a first IO protocol, and the second type of IO protocol controller is used to implement a second IO protocol; The defect information includes: A plurality of the first-type IO protocol controllers are all valid, and one or more of the second-type IO protocol controllers are invalid, and the core domains of the management configuration modules in the plurality of the second-type IO protocol controllers are all valid; or, A plurality of the second IO protocol controllers are all valid, and one or more of the first type IO protocol controllers are invalid, and the core domains of the management configuration modules in the plurality of the first type IO protocol controllers are all valid; or, The core domain of the management configuration module of at least one first-type IO protocol controller among the plurality of first-type IO protocol controllers fails; or, A core domain of a management configuration module of at least one second-type IO protocol controller among the plurality of second-type IO protocol controllers fails.

5. The method according to claim 4, characterized in that The recycling type includes a first recyclable state, a second recyclable state and a non-recyclable state; wherein the first recyclable state corresponds to the implementation of the first IO protocol, and the second recyclable state corresponds to the implementation of the second IO protocol; The step of determining the recovery type of the IO chip according to the defect information includes: If the defect information indicates that the plurality of the first-type IO protocol controllers are all valid, and one or more of the second-type IO protocol controllers are invalid, and the core domains of the management configuration modules in the plurality of the second-type IO protocol controllers are all valid, it is determined that the IO core is in the first recyclable state; If the defect information indicates that the plurality of the second IO protocol controllers are all valid, and one or more of the first type IO protocol controllers are invalid, and the core domains of the management configuration modules in the plurality of the first type IO protocol controllers are all valid, it is determined that the IO chip is in the second recyclable state; If the defect information is that the core domain of the management configuration module of at least one first-type IO protocol controller among multiple first-type IO protocol controllers has failed; or, the core domain of the management configuration module of at least one second-type IO protocol controller among multiple second-type IO protocol controllers has failed, it is determined that the IO chip is in an unrecyclable state.

6. The method according to claim 5, characterized in that If the IO chip is in the first recyclable state and / or the second recyclable state, packaging the IO chip of the corresponding recycling type according to the packaging position to obtain a recycled chip; If the IO chip is in an unrecyclable state, the IO chip is discarded.

7. The method according to claim 6, characterized in that The packaging position includes a first packaging position and a second packaging position; According to the packaging position, packaging the IO chip of the corresponding recycling type includes: When the IO chip is in a first recyclable state, packaging the IO chip to the first packaging position; When the IO chip is in the second recyclable state, the IO chip is packaged to the second packaging position.

8. The method according to claim 1, characterized in that After packaging the IO chips of the corresponding recycling type according to the packaging position to obtain the recycled chips, the method further includes: Initialize the recycling chip, check the position identification of the IO chip, put the idle IO protocol controller in the IO chip into a low power consumption state, turn off its clock signal, and put the reset signal into a valid state; wherein the position identification of the IO chip is used to mark the usage status of multiple IO protocol controllers of the IO chip.

9. A bad film recovery device, characterized in that: include: A chip acquisition unit is used to acquire a preset chip, wherein the preset chip at least includes an IO core particle, wherein the IO core particle has a plurality of IO protocol controllers of different types, and the plurality of IO protocol controllers of different types share a physical layer, and are used to implement different IO protocols; wherein, corresponding to the implementation of different IO protocols, the IO core particles are provided with different packaging positions in the preset chip; A test determination unit, used to test the multiple IO protocol controllers to determine the recovery type of the IO core particles, wherein the recovery type corresponds to the failure conditions of the multiple IO protocol controllers and is used to indicate the recovery state of the IO core particles; The bad chip packaging unit is used to package the IO core particles of the corresponding recycling type according to the packaging position to obtain recycled chips.

10. The bad film recovery device according to claim 9, characterized in that: Also includes: The initialization unit is used to initialize the recycling chip, check the position identification of the IO chip, put the idle IO protocol controller in the IO chip into a low power consumption state, turn off its clock signal, and put the reset signal into a valid state; wherein the position identification of the IO chip is used to mark the usage status of multiple IO protocol controllers of the IO chip.

11. A chip, characterized in that: The chip is recovered based on the bad chip recovery method according to any one of claims 1 to 8.

12. A computing device, characterized in that: It comprises the bad film recovery device as described in any one of claims 9 to 10.

13. A storage medium, characterized in that: The storage medium stores one or more computer executable instructions, and when the one or more computer executable instructions are executed, the bad chip recycling method according to any one of claims 1 to 8 is implemented.

14. A computer program product, characterized in that It comprises one or more computer executable instructions, and when the one or more computer executable instructions are executed, the bad chip recycling method as claimed in any one of claims 1 to 8 is implemented.