Storage device repair method and storage device repair system

Abstract

The present application provides a method for repairing a storage device and a system for repairing a storage device. The storage device includes a storage array and a redundant storage array, wherein the redundant storage cells in the redundant storage array are used to repair and replace failed storage cells in the storage array. The repair method includes obtaining position information of failed storage cells in the storage array, wherein the position information includes first-direction position information and second-direction position information; constructing a first set and a second set based on the position information of the failed storage cells, and constructing a bipartite graph, wherein the first set is a set of first-direction position information of failed storage cells, and the second set is a set of second-direction position information of failed storage cells; obtaining a target failure point of the maximum match of the bipartite graph, and confirming a repair strategy based on the target failure point. By the above-mentioned method, the repair rate of failed storage cells in the storage device can be improved, and the qualified rate of mass production of storage devices can be improved.

Description

Technical Field

[0001] The present application relates to the field of storage technology, and in particular to a method for repairing a storage device and a system for repairing a storage device. Background Art

[0002] Dynamic Random Access Memory (DRAM) chips, as a storage device, are now widely used in mobile phones, computers, servers, and other devices due to their advantages such as simple structure, high integration, and low power consumption, playing an important role in the consumer electronics field. During the DRAM chip manufacturing process, failed memory cells may appear in the DRAM chip's memory array. To cope with this situation, a portion of redundant storage area is reserved during DRAM chip design, such as a redundant memory array including multiple redundant memory cells, to replace failed memory cells in the memory array to ensure that the DRAM chip can be used normally. Currently, existing methods for repairing failed memory cells in a memory array count and sort the number of failed memory cells, and then, after all the redundant resources in a certain direction have been used up, repair is performed in another direction. This repair method has poor repair effects and cannot guarantee that the redundant resources ultimately used are minimized, resulting in a waste of redundant resources. Therefore, it is very important to use limited redundant resources to repair as many failed memory cells as possible and improve the repair rate of failed memory cells. Summary of the Invention

[0003] In order to solve the above problems, the present application provides a storage device repair method and a storage device repair system, which can improve the repair rate of failed storage units in the storage device and improve the pass rate of mass production of storage devices.

[0004] A technical solution adopted in the present application is: providing a method for repairing a storage device, wherein the storage device includes a storage array and a redundant storage array, and the redundant storage cells in the redundant storage array are used to repair and replace failed storage cells in the storage array, and the repair method includes obtaining position information of the failed storage cells in the storage array, wherein the position information includes first-direction position information and second-direction position information; constructing a first set and a second set based on the position information of the failed storage cells, and constructing a bipartite graph, wherein the first set is a set of first-direction position information of the failed storage cells, and the second set is a set of second-direction position information of the failed storage cells; obtaining a target failure point of the maximum match of the bipartite graph, and confirming a repair strategy based on the target failure point.

[0005] The method includes obtaining the maximum matching target failure point of the bipartite graph and confirming the repair strategy based on the target failure point, which includes obtaining the maximum matching target failure point of the bipartite graph; traversing the target failure points and confirming the failure direction of each target failure point; and confirming the repair strategy based on the failure direction of each target failure point.

[0006] Wherein, obtaining the target failure point of the maximum match of the bipartite graph includes sorting the first elements in the first set and sorting the second elements in the second set; sequentially searching for the matching second elements of the first elements in the first set according to the association path, and forming the target failure point with the first element and the matching second element, wherein the association path represents the first direction position information and the second direction position information of a failed storage unit corresponding to the first element and the second element.

[0007] Among them, the first elements in the first set are searched for their matching second elements in the second set according to the valid path in sequence, and the first element and the matching second element constitute the target failure point, including searching for the temporary matching second element in the second set for the current first element in the first set according to the associated path, wherein the temporary matching second element is the second element in the second set that has an associated path with the current first element and is ranked first; determining whether the temporary matching second element of the current first element is the temporary matching second element of the previous first element; in response to the temporary matching second element of the current first element being the temporary matching second element of the previous first element, determining whether the temporary matching second element is the only matching second element of the previous first element; in response to the temporary matching second element If it is not the only matching second element for the previous first element, search for other temporarily matching second elements that are sorted before it in the second set according to the association path as the updated temporary matching second element of the previous first element, wherein the updated temporary matching second element is the first second element in the second set that has an association path with the previous first element after the temporary matching second element; update the next first element sorted in the first set as the current first element, and repeat the above steps until all first elements in the first set have found a temporary matching second element, and the temporary matching second element of any first element is different from the temporary matching second elements of other first elements, and the temporary matching second elements are respectively used as the matching second elements of the corresponding first element.

[0008] Among them, the first elements in the first set are searched for their matching second elements in the second set according to the valid path in sequence, and the first element and the matching second element constitute the target failure point. It also includes, in response to the temporary matching second element being the only matching second element of the previous first element, searching for other temporary matching second elements that are ranked before the current first element in the second set according to the associated path as the updated temporary matching second element of the current first element, wherein the updated temporary matching second element is the first second element in the second set that has an associated path with the current first element after the temporary matching second element.

[0009] Among them, traversing the target failure points and confirming the failure direction of each target failure point includes confirming a first number of failed storage cells in the same storage row / column as the current target failure point in a first direction, wherein the first number of failed storage cells includes the current target failure point; confirming a second number of failed storage cells in the same storage column / row as the current target failure point in a second direction, wherein the second number of failed storage cells includes the current target failure point; determining the failure direction of the current target failure point based on the first number and the second number; updating the next target failure point to the current target failure point, and repeating the above steps to traverse all target failure points and confirm the failure direction of each target failure point.

[0010] Wherein, based on the first number and the second number, determining the failure direction of the current target failure point includes, in response to the first number being greater than the second number, determining the failure direction of the current target failure point to be the first direction corresponding to the first number; or in response to the first number being less than the second number, determining the failure direction of the current target failure point to be the second direction corresponding to the second number; or in response to the first number being equal to the second number, determining the failure direction of the current target failure point to be one of the first direction or the second direction.

[0011] Among them, based on the failure direction of each target failure point, the repair strategy is confirmed, including:

[0012] Based on the failure direction of each target failure point, a third number of target failure points having a failure direction in a first direction is counted, and a fourth number of target failure points having a failure direction in a second direction is counted; in response to the third number being not greater than the number of redundant resources in the first direction in the redundant storage array, and the fourth number being not greater than the number of redundant resources in the second direction in the redundant storage array, according to the failure direction of each target failure point, the storage cells in the corresponding storage row / column where each target failure point is located are repaired and replaced using the redundant resources in the first direction and / or the redundant resources in the second direction corresponding to the failure direction.

[0013] Among them, according to the failure direction of each target failure point, the first direction redundant resources and / or the second direction redundant resources corresponding to the failure direction are used to repair and replace the storage cells of the corresponding storage row / column where each target failure point is located, including: in response to the failure direction of the current target failure point being the first direction, using a redundant storage row / column first direction redundant resource to repair and replace the storage cells of the corresponding storage row / column where the current target failure point is located; or in response to the failure direction of the current target failure point being the second direction, using a redundant storage column / row second direction redundant resource to repair and replace the storage cells of the corresponding storage column / row where the current target failure point is located.

[0014] Wherein, based on the failure direction of each target failure point, confirming the repair strategy also includes, in response to the third number being greater than the number of redundant resources in the first direction in the redundant storage array, performing a first sorting on the first target failure point with the failure direction in the first direction according to a first number of failed storage cells in the same storage row / column as the first target failure point in the first direction; using the redundant resources in the first direction to repair and replace the storage cells in the corresponding storage rows / columns of some first target failure points in the first sorting order in sequence according to the result of the first sorting, until the redundant resources in the first direction are exhausted; eliminating the repaired failed storage cells in the storage array to update the failed storage cells in the storage array; counting the fifth number of failed storage cells in each storage column / row extending along the second direction in the storage array after the update, and performing a second sorting; using the redundant resources in the second direction to repair the failed storage cells in each storage column / row extending along the second direction in sequence according to the result of the second sorting, until the redundant resources in the second direction are exhausted.

[0015] Wherein, based on the failure direction of each target failure point, confirming the repair strategy also includes, in response to the fourth number being greater than the number of redundant resources in the second direction in the redundant storage array, performing a third sorting on the second target failure point with the failure direction in the second direction according to the second number of failed storage cells in the same storage column / row as the second target failure point in the second direction; using the redundant resources in the second direction to repair and replace the storage cells in the corresponding storage columns / rows of some second target failure points in the first sorting order in sequence according to the result of the third sorting, until the redundant resources in the second direction are exhausted; eliminating the repaired failed storage cells in the storage array to update the failed storage cells in the storage array; counting the sixth number of failed storage cells in each storage row / column extending along the first direction in the storage array after the update, and performing a fourth sorting; using the redundant resources in the first direction to repair the failed storage cells in each storage row / column extending along the first direction in sequence according to the result of the fourth sorting, until the redundant resources in the first direction are exhausted.

[0016] Another technical solution adopted in the present application is: providing a repair system for a storage device, the repair system including a main control device and a storage device, the main control device being used to execute the above-mentioned repair method to generate repair replacement information; the storage device being coupled to the main control device, wherein the storage device includes a storage grain, the storage grain includes at least one storage block, and each storage block includes a storage array and a redundant storage array.

[0017] The storage device further includes a control chip, which is packaged together with the storage chip, and the control chip receives the repair and replacement information.

[0018] The beneficial effects of the embodiments of the present application are as follows: the storage device repair method provided by the present application obtains the position information of the failed storage unit of the storage array, constructs a first set whose set elements are the first-direction position information of the failed storage unit and a second set whose set elements are the second-direction position information of the failed storage unit based on the position information of the failed storage unit, and constructs a bipartite graph about the position information of the failed storage unit based on the first set and the second set, finally obtains the maximum matching target failure point of the bipartite graph based on the bipartite graph, and confirms the repair strategy based on the target failure point, that is, determines the minimum redundant resources required for repairing the failed storage unit of the storage array through the position information of the target failed storage unit, and thus confirms the repair strategy based on the minimum redundant resources required for repairing the storage array, so as to improve the utilization rate of redundant resources, thereby improving the repair rate of the failed storage units of the storage array, and further improving the product pass rate of the storage device. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. 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 any creative work.

[0020] in:

[0021] Figure 1 is a structural diagram of an embodiment of a storage device provided by the present application;

[0022] Figure 2 This is a flowchart of an embodiment of a method for repairing a storage device provided by the present application;

[0023] Figure 3 This application provides information about the location of the failed storage unit. Figure 1 A schematic structural diagram of an embodiment;

[0024] Figure 4 This application Figure 2A schematic flow chart of an embodiment of step S300 in the embodiment;

[0025] Figure 5 This application Figure 4 A schematic flow chart of an embodiment of step S310 in the embodiment;

[0026] Figure 6 yes Figure 3 Schematic diagram of matching a first element in a first set with a second element in a second set according to an association path;

[0027] Figure 7 This application Figure 5 A flow chart of an embodiment of step S312 in the embodiment;

[0028] Figure 8 This application provides the Figure 3 Schematic diagram of the process of maximum matching of a bipartite graph in the embodiment;

[0029] Figure 9 This application Figure 5 A flow chart of another embodiment of step S312 in the embodiment;

[0030] Figure 10 yes Figure 8 Another schematic diagram of the process of finding the maximum matching of a bipartite graph according to an embodiment;

[0031] Figure 11 This application Figure 4 A schematic flow chart of an embodiment of step S320 in the embodiment;

[0032] Figure 12 This application Figure 4 A flow chart of an embodiment of step S330 in the embodiment;

[0033] Figure 13 yes Figure 4 A schematic flow chart of another embodiment of step S330 in the embodiment;

[0034] Figure 14 yes Figure 4 A schematic flow chart of another embodiment of step S330 in the embodiment;

[0035] Figure 15 This is a flow chart of another embodiment of the method for repairing a storage device provided by the present application;

[0036] Figure 16 This is a structural diagram of an embodiment of a repair system for a storage device provided by the present application;

[0037] Figure 17 yes Figure 16A schematic structural diagram of another embodiment of the storage device in the embodiment. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It will be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only some, rather than all, structures related to the present application are shown in the drawings. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0039] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0040] See Figure 1 , Figure 1 This is a schematic diagram of the structure of an embodiment of the storage device provided by this application. Figure 1As shown, a memory device includes a memory array and a redundant memory array, wherein the memory array includes memory rows and memory columns, wherein the memory rows can be referred to as word lines WL, and the memory columns can be referred to as bit lines BL. When the memory rows extend along a first direction, the corresponding memory columns extend along a second direction, and multiple memory rows are sequentially spaced apart in the second direction, and multiple memory columns are sequentially spaced apart in the first direction; or when the memory rows extend along the second direction, the corresponding memory columns extend along the first direction, and multiple memory rows are sequentially spaced apart in the first direction, and multiple memory columns are sequentially spaced apart in the second direction. The redundant memory array includes redundant memory rows (YWL) and / or redundant memory columns (YBL), and the redundant memory rows and / or redundant memory columns can be referred to as redundant resources. When the redundant memory rows extend along the first direction, the redundant memory columns extend along the second direction, and multiple redundant memory rows are sequentially spaced apart in the second direction, and multiple redundant memory rows are sequentially spaced apart in the first direction; or when the redundant memory rows extend along the second direction, the redundant memory columns extend along the first direction, and multiple redundant memory rows are sequentially spaced apart in the first direction, and multiple redundant memory columns are sequentially spaced apart in the second direction. The redundant storage rows extend in the same direction as the storage rows, and the redundant storage columns extend in the same direction as the storage columns. The redundant storage cells in the redundant storage array can be used to repair and replace failed storage cells in the storage array. It can be understood that using the redundant storage rows / columns in the redundant storage array to repair or replace storage rows / columns in the storage array refers to mapping the addresses of the storage rows / columns in the storage array to the addresses of the redundant storage rows / columns. For example, the address of a storage row in the storage array is mapped to the address of a redundant storage row to repair and replace a failed storage cell in that storage row.

[0041] The present application provides a method for repairing a storage device. The method can be applied to the above-mentioned storage device, that is, the execution subject of the repair method can be the storage device, and the execution subject of the repair method can also be an electronic device including the storage device, etc. The execution subject of the repair method is not specifically limited here. Figure 2 , Figure 2 FIG. 1 is a flow chart of an embodiment of a method for repairing a storage device provided by the present application. Figure 2 As shown, the repair method includes the following steps:

[0042] Step S100: obtaining location information of a failed storage unit in a storage array.

[0043] A storage array includes storage cells, wherein when data is written to and read from the storage cells, if the written data is consistent with the read data, the storage cell is considered a normal storage cell; if the written data is inconsistent with the read data, the storage cell is considered a failed storage cell, i.e., a failed storage cell. To obtain the position information of failed storage cells in the storage array, preset data can be written to all storage cells in the storage array, the actual data read can be compared with the preset data, and the storage cells with inconsistent comparison results can be considered failed storage cells in the storage array, while the position information of each failed storage cell is obtained. The position information of the storage cells includes first-direction position information and second-direction position information. The first-direction position information can be a storage row / column in the storage array, and the corresponding second-direction position information is a storage column / row in the storage array; the first-direction position information can be a bit line / word line in the storage array, and the corresponding second-direction position information is a word line / bit line in the storage array.

[0044] Step S200: constructing a first set and a second set based on the location information of the failed storage unit, and constructing a bipartite graph.

[0045] Based on the location information of the failed storage units, the location information of the failed storage units is classified to construct a first set including the first direction location information of the failed storage units and a second set including the second direction location information of the failed storage units. At the same time, based on the first set and the second set, a bipartite graph of the location information of the failed storage units is constructed. Figure 3 , Figure 3 This application provides information about the location of the failed storage unit. Figure 1 A schematic diagram of the structure of an embodiment, in which the dots correspond to the location information of failed storage units, the X-axis corresponds to the first direction, and the Y-axis corresponds to the second direction; or the X-axis corresponds to the second direction, and the Y-axis corresponds to the first direction. A bipartite graph is a special model in graph theory, whose vertex set V can be divided into two non-intersecting parts M and N, such that the two endpoints of any edge in the graph are in M ​​and N, respectively. A matching of a bipartite graph refers to a subset E' of its edge set E, such that no two edges in E' share vertices. These features of the bipartite graph correspond exactly to the location information of failed storage units.

[0046] Step S300: Obtain a target failure point of a maximum match of a bipartite graph, and confirm a repair strategy based on the target failure point.

[0047] In bipartite graph theory, there is a minimum point cover problem, which is to find the minimum number of points so that all edges of the bipartite graph have at least one endpoint among these points. Conversely, by deleting the edges containing these points, all edges can be deleted. This problem corresponds to the problem of repairing failed storage units in a storage array, which is to determine the edges containing these minimum points, that is, to determine the number of redundant resources required to repair the failed storage units in the storage array and the location information of the repaired failed storage units. Based on the location information of the failed storage units, a bipartite graph is constructed to obtain the target failure point of the maximum matching of the bipartite graph, that is, to obtain the target failure point in the failed storage units of the storage array that can achieve the maximum matching of the bipartite graph. The target failure point refers to the location information corresponding to the failed storage unit that can achieve the maximum matching. It can be understood that one target failure point corresponds to the location information of one failed storage unit. The repair strategy is confirmed based on the target failure point, that is, the repair strategy is confirmed based on the location information of the target failed storage unit, thereby confirming the repair strategy based on the minimum redundant resources required to repair the storage array.

[0048] The present application provides a method for repairing a storage device, which obtains position information of a failed storage unit of a storage array, constructs a first set whose set elements are first-direction position information of the failed storage unit and a second set whose set elements are second-direction position information of the failed storage unit based on the position information of the failed storage unit, and constructs a bipartite graph about the position information of the failed storage unit based on the first set and the second set. Finally, based on the bipartite graph, a target failure point of the maximum match of the bipartite graph is obtained, and a repair strategy is confirmed based on the target failure point. That is, the minimum redundant resources required for repairing the failed storage unit of the storage array are determined through the position information of the target failed storage unit, and the repair strategy is confirmed based on the minimum redundant resources required for repairing the storage array, so as to improve the utilization rate of redundant resources, thereby improving the repair rate of the failed storage units of the storage array, and further improving the product pass rate of the storage device.

[0049] Optionally, see Figure 4 , Figure 4 This application Figure 2 The flowchart of step S300 in the embodiment is as follows: Figure 4 As shown, step S300 can implement the target failure point based on the maximum matching of the bipartite graph to confirm the repair strategy of the storage array through the following steps.

[0050] Step S310: Obtain the target failure point of the maximum matching of the bipartite graph.

[0051] The maximum matching target failure point of the bipartite graph about the location information of the failed storage unit is obtained, that is, the location information of the target failed storage unit that can confirm the minimum redundant resources required to completely eliminate the failed storage units in the storage array is obtained.

[0052] Step S320: traverse the target failure points and confirm the failure direction of each target failure point.

[0053] When there are one or more target failure points for the maximum match, the target failure points are traversed to determine the failure direction of each target failure point. The failure direction of the target failure point refers to the direction with the largest number of failed storage units in the direction of the target failure point.

[0054] Step S330: confirming a repair strategy based on the failure direction of each target failure point.

[0055] Based on the failure direction of each target failure point, a repair strategy for failed storage units in the storage array is determined.

[0056] This embodiment obtains the maximum matching target failure point of the bipartite graph and determines the maximum failure direction of each target failure point, thereby determining the repair strategy based on the maximum failure direction of the target failure point, thereby improving the utilization rate of redundant resources, and further improving the repair rate of failed storage units in the storage array, thereby further improving the product pass rate of the storage device.

[0057] Optionally, see Figure 5 , Figure 5 This application Figure 4 The flowchart of step S310 in the embodiment is as follows: Figure 5 As shown, step S310 of obtaining the target failure point of the maximum matching of the bipartite graph can be achieved by the following steps, which specifically include:

[0058] Step S311: sort the first elements in the first set, and sort the second elements in the second set.

[0059] The first set is a set of first-direction position information of failed storage units, that is, the first set includes the first-direction position information of all failed storage units in the storage array. Sorting the first elements in the first set can be understood as sorting the first-direction positions of the failed storage units. Similarly, the second set is a set of second-direction position information of failed storage units. Sorting the second elements in the second set is equivalent to sorting the second-direction positions of the failed storage units. Figure 3 , the first element can be x1, x2, x3, etc., and the second element can be y2, y4, y0, y6, y3, etc.

[0060] Step S312: sequentially searching for matching second elements in the second set for the first elements in the first set according to the association paths, and forming a target failure point with the first elements and the matching second elements.

[0061] The first element in the first set is sequentially searched for its matching second element in the second set according to the association path, and the first element and the matching second element constitute the target failure point. It can be understood that according to the sorted order, the first element is sequentially searched for its matching second element in the second set according to the association path, that is, according to the sorted order, the first direction position information is sequentially searched for matching second direction position information according to the association path. When the first direction position information matches the second direction position information according to the association path, the position information of the target failed storage unit with the maximum match can be constituted. Among them, the association path represents the first direction position information and the second direction position information of a failed storage unit corresponding to the first element and the second element, see Figure 6 , Figure 6 yes Figure 3 The embodiment is a schematic diagram of matching a first element in a first set with a second element in a second set according to an association path.

[0062] Optionally, see Figure 7 , Figure 7 This application Figure 5 The flowchart of step S312 in the embodiment is as follows: Figure 7 As shown, step S312 can be implemented through steps S3121 to S3125, and see the following for details:

[0063] Step S3121: searching for a temporary matching second element in the second set for the current first element in the first set according to the association path.

[0064] The current first element is selected in the sorted order. Then, the current first element is searched for its temporary matching second element in the second set according to the sorting order of the second elements, following the association path. If one or more second elements match the current first element during the search, the first-ranked second element among the one or more second elements matching the first element is selected as the temporary matching second element. That is, the temporary matching second element is the second element in the second set that has an association path with the current first element and ranks first.

[0065] Step S3122: Determine whether the temporary matching second element of the current first element is the temporary matching second element of the previous first element.

[0066] When searching for matching second elements in the second set for the first elements in the first set according to the association path, if there are multiple first elements matching the same second element, then when the current first element finds its matching first-ranked second element according to the association path, it is further determined whether the second element is a temporary matching second element of the previous first element.

[0067] Step S3123: In response to the temporary matching second element of the current first element being the temporary matching second element of the previous first element, determine whether the temporary matching second element is the only matching second element of the previous first element.

[0068] In response to the temporary matching second element of the current first element and the temporary matching second element of the previous first element being the same second element, it is further determined whether the temporary matching second element is the only matching second element of the previous first element.

[0069] Step S3124: In response to the temporary matching second element not being the only matching second element for the previous first element, search for other temporary matching second elements that are sorted before the previous first element in the second set according to the association path to serve as the updated temporary matching second element of the previous first element.

[0070] If the previous first element has other matching second elements besides the temporarily matching second element, then the previous first element is searched for other temporarily matching second elements that are sorted before it in the second set according to the association path as the updated temporary matching second elements of the previous first element, that is, the updated temporary matching second element is the first second element in the second set that has an association path with the previous first element after the temporarily matching second element.

[0071] Step S3125: Update the next first element sorted in the first set as the current first element, repeat steps S3121 to S3124 until all first elements in the first set have found a temporary matching second element, and the temporary matching second element of any first element is different from the temporary matching second elements of other first elements, and the temporary matching second elements are respectively used as the matching second elements of the corresponding first elements.

[0072] Update the next first element sorted in the first set as the current first element, and repeat steps S3121 to S3124 until all first elements in the first set have found temporary matching second elements, and the temporary matching second element of any first element is different from the temporary matching second elements of other first elements, and the temporary matching second elements are respectively used as the matching second elements of the corresponding first elements.

[0073] For an example, see Figure 8 , Figure 8 This application provides the Figure 3 Schematic diagram of the process of maximum matching of bipartite graph in the embodiment. The first elements of the first set are: x1, x2, x3, x4, x5, x6; the second elements of the second set are: y0, y2, y3, y4, y6, y11, y12, y14. Figure 8As shown, according to the sorting, x1 is used as the current first element to search for a temporary matching second element along the associated path. x1 matches y0 and y2, and y0 is ranked first, so y0 is used as the temporary matching second element of x1. The next first element is updated to the current first element, and the search continues from x2. x2 matches y4, and y4 and y0 are two second elements. y4 is used as the temporary matching second element of x2. The search continues from x3. x3 matches y0, y12, and y14. y0 is ranked first, but y0 has already been used as the temporary matching second element of x1. Therefore, the search returns to x1, y2 is used as the temporary matching second element of x1, and y0 is used as the temporary matching second element of x3. Repeat the above steps until all first elements in the first set are traversed and all target failure points are found.

[0074] Based on the above embodiments, see Figure 9 , Figure 9 This application Figure 5 A flow chart of another embodiment of step S312 in the embodiment, Figure 7 Based on the embodiment shown, step S312 further includes the following steps:

[0075] Step S3126: In response to the temporary matching second element being the only matching second element of the previous first element, search for other temporary matching second elements that are sorted before the current first element in the second set according to the association path to serve as the updated temporary matching second element of the current first element, wherein the updated temporary matching second element is the first second element in the second set that has an association path with the current first element after the temporary matching second element.

[0076] In response to the provisional matching second element being the only matching second element for the previous first element, a search is performed for the current first element according to the association path for another provisional matching second element that is ranked earlier in the second set, to serve as an updated provisional matching second element for the current first element. The updated provisional matching second element is the first second element in the second set that follows the provisional matching second element and has an association path with the current first element.

[0077] For an example, see Figure 8 and Figure 10 , Figure 10 yes Figure 8 Another schematic diagram of the process of finding the maximum matching of a bipartite graph in an embodiment. The first elements of the first set are: x1, x2, x3, x4, x5, x6; the second elements of the second set are: y0, y2, y3, y4, y6, y11, y12, y14. Figure 8As shown, according to the sorting, x1 is used as the current first element to search for the temporary matching second element according to the associated path. x1 matches y0 and y2, and y0 is ranked first, so y0 is used as the temporary matching second element of x1; the next first element is updated to the current first element, and the search continues from x2. x2 matches y4. y4 and y0 are two second elements, so y4 is used as the temporary matching second element of x2; the search continues from x3. x3 matches y0, y12 and y14. y0 is in the front, but y0 has been used as the temporary matching second element of x1, so it returns to x1, and uses y2 as the temporary matching second element of x1, and y0 as the temporary matching second element of x3; the search continues when the current first element is x4. x4 matches y4, and y4 is used as the temporary matching second element of x4, but y4 is already the temporary matching second element of x2, and y4 is the only matching second element of x2, and y4 is also the only matching second element of x4, so x4 has no temporary matching second element. Continue to traverse the first element behind, and finally find all the target failure points as (x1, y2), (x2, y4), (x3, y12), and (x5, y0).

[0078] Optionally, see Figure 11 , Figure 11 This application Figure 4 The flowchart of step S320 in the embodiment is as follows: Figure 11 As shown, step S320 confirming the failure direction of each target failure point can be achieved by the following steps, which specifically include:

[0079] Step S321: confirming a first number of failed storage cells in a first direction that are in the same storage row / column as the current target fail point.

[0080] Confirm the number of failed memory cells in the same storage row / column as the current target failure point in the first direction, that is, confirm the first number of failed memory cells in the same storage row / column as the target failed memory cell in the first direction, wherein the first number of failed memory cells includes the current target failed memory cell, that is, includes the current target failure point. For example, when the storage row is a storage row extending along the first direction, the number of failed memory cells in the storage row where the target failed memory cell is located is the first number. Figure 3 , its failure target points are (x1, y2), (x2, y4), (x3, y12), and (x5, y0). When the current failure target point is (x2, y4), the first number of failed memory cells in the same storage row as the failure target point (x2, y4) in the first direction, i.e., the X-axis direction, is 3. The number of failed memory cells in the second direction, i.e., the Y-axis direction, is 1.

[0081] Step S322: Determine a second number of failed memory cells in a second direction that are in the same storage column / row as the current target fail point.

[0082] Similarly, the number of failed memory cells in the second direction that are in the same storage row / column as the current target failure point is determined, that is, the second number of failed memory cells in the second direction that are in the same storage column / row as the target failed memory cell is determined, wherein the second number of failed memory cells includes the current target failed memory cell, that is, includes the current target failure point. For example, when the storage rows are storage rows extending along the first direction, the corresponding storage columns are storage columns extending along the second direction, and the number of failed memory cells in the storage column where the target failed memory cell is located is the second number. Figure 3 , its failure target points are (x1, y2), (x2, y4), (x3, y12) and (x5, y0). When the current failure target point is (x2, y4), the second number of failed storage cells on the same storage column of the failure target point (x2, y4) in the second direction, i.e., the Y-axis direction, is 1.

[0083] Step S323: Determine the failure direction of the current target failure point based on the first quantity and the second quantity.

[0084] The failure direction of the current target failure point is determined based on a first number of failed storage cells in the first direction of the target failure point and a second number of failed storage cells in the second direction of the target failure point. For example, if the number of failed storage cells in the first direction of the current target failure point is 3 and the number of failed storage cells in the second direction is 1, the failure direction of the current target failure point is determined to be the first direction.

[0085] Step S324: Update the next target failure point as the current target failure point, and repeat steps S321 to S323 to traverse all target failure points and confirm the failure direction of each target failure point.

[0086] The next target failure point is updated as the current target failure point, and the step of confirming the failure direction based on the first quantity and the second quantity is continued to traverse all target failure points, thereby confirming the failure direction of each target failure point.

[0087] This embodiment obtains the first number and the second number of failed storage cells in the same storage row / column as the target failure point in the first direction and the second direction for each target failure point, and confirms the failure direction of the target failure point based on the first number and the second number. The process is simple and easy to implement, and can quickly determine the failure direction of the target failure point, thereby improving the repair efficiency of failed storage cells in the storage array.

[0088] Optionally, step S323 may be implemented by the following steps, specifically including:

[0089] Step S3231: In response to the first number being greater than the second number, determining the failure direction of the current target failure point to be the first direction corresponding to the first number.

[0090] If a first number of failed memory cells in the first direction and in the same storage row / column as the current target failure point is greater than a second number of failed memory cells in the second direction and in the same storage column / row as the current target failure point, then in response to the first number being greater than the second number, the failure direction of the current target failure point is determined to be the first direction corresponding to the first number. Or

[0091] Step S3232: In response to the first number being smaller than the second number, determining the failure direction of the current target failure point to be the second direction corresponding to the second number.

[0092] If a first number of failed memory cells in the first direction and in the same storage row / column as the current target failure point is less than a second number of failed memory cells in the second direction and in the same storage column / row as the current target failure point, in response to the first number being less than the second number, the failure direction of the current target failure point is determined to be the second direction corresponding to the second number; or

[0093] Step S3233: In response to the first number being equal to the second number, determining that the failure direction of the current target failure point is one of the first direction or the second direction.

[0094] If a first number of failed storage cells in the first direction and on the same storage row / column as the current target failure point is equal to a second number of failed storage cells in the second direction and on the same storage column / row as the current target failure point, in response to the first number being equal to the second number, it is determined that the failure direction of the current target failure point is one of the first direction or the second direction.

[0095] Optionally, see Figure 12 , Figure 12 This application Figure 4 The flowchart of step S330 in the embodiment is as follows: Figure 12 As shown, step S330 includes the following steps:

[0096] Step S331: Based on the failure direction of each target failure point, counting a third number of target failure points with a failure direction in a first direction, and counting a fourth number of target failure points with a failure direction in a second direction.

[0097] Based on the failure direction of each target failure point, the failure directions of the target failure points are classified and counted. Specifically, the failure directions are divided into a first direction and a second direction. The number of target failure points with the first direction as the failure direction is counted, and the number of target failure points with the first direction as the failure direction is used as the third quantity. Similarly, the number of target failure points with the second direction as the failure direction is counted, and the number of target failure points with the second direction as the failure direction is used as the fourth quantity.

[0098] Step S332: In response to the third number being not greater than the number of first-direction redundant resources in the redundant storage array and the fourth number being not greater than the number of second-direction redundant resources in the redundant storage array, according to the failure direction of each target failure point, the first-direction redundant resources and / or the second-direction redundant resources corresponding to the failure direction are used to repair and replace the storage cells in the corresponding storage row / column where each target failure point is located.

[0099] The third number of target failure points with a failure direction in the first direction and the number of redundant resources in the first direction in the redundant storage array are determined, i.e., the third number and the number of redundant storage rows / columns extending along the first direction in the redundant storage array are determined. Similarly, the fourth number and the number of redundant resources in the second direction in the redundant storage array are determined, i.e., the fourth number and the number of redundant storage columns / rows extending along the second direction in the redundant storage array are determined. In response to the third number being not greater than the number of redundant resources in the first direction in the redundant storage array, and the fourth number being not greater than the number of redundant resources in the second direction in the redundant storage array, i.e., the redundant resources in the first direction and the redundant resources in the second direction in the redundant storage array can meet the redundant resources required to repair and replace failed storage cells in the storage array, the storage cells in the corresponding storage row / column where each target failure point is located are repaired and replaced using the redundant resources in the first direction and / or the redundant resources in the second direction corresponding to the failure direction according to the failure direction of each target failure point. It can be understood that the first-direction redundant resources and / or the second-direction redundant resources corresponding to the failure direction are used to repair and replace the storage cells of the corresponding storage row / column where each target failure point is located, and the address of the corresponding storage row / column where each target is located is mapped to the address of a redundant storage row / column corresponding to the first-direction redundant resources and / or the second-direction redundant resources corresponding to the failure direction, so as to realize the repair and replacement of the failed storage cells on the storage row / column.

[0100] Optionally, step 332 may be implemented through step S3321 or step S3322. For details, see the following text:

[0101] Step S3321: In response to the failure direction of the current target failure point being the first direction, a redundant storage row / column first direction redundant resource is used to repair and replace a storage unit in the corresponding storage row / column where the current target failure point is located.

[0102] In response to the failure direction of the current target failure point being the first direction, a redundant storage row / column in the redundant resources of the first direction is used to repair and replace the storage unit of the corresponding storage row / column where the current target failure point is located. That is, the address of the corresponding storage row / column where the current target failure point is located is mapped to the address of a redundant storage row / column to achieve the repair and replacement of the storage unit of the corresponding storage row / column where the current target failure point is located. Or

[0103] Step S3322: In response to the failure direction of the current target failure point being the second direction, using a redundant storage column / row with the second direction redundant resources to repair and replace the storage cell of the corresponding storage column / row where the current target failure point is located.

[0104] In response to the failure direction of the current target failure point being the second direction, a redundant storage column / row in the redundant resources in the second direction is used to repair and replace the storage cell of the corresponding storage column / row where the current target failure point is located.

[0105] For example, the third number is 3 and the fourth number is 2, that is, the minimum redundant resources required for the failed storage cells in the storage array are 3 redundant storage rows extending along the first direction and 2 redundant storage columns extending along the second direction. When the number of redundant storage rows extending along the first direction in the redundant storage array is 5 and the number of redundant storage columns extending along the second direction in the redundant storage array is 4, the three redundant storage rows extending along the first direction are used to repair and replace the storage cells on the corresponding storage rows where the three target failure points are located in a one-to-one manner, and the two redundant storage columns extending along the second direction are used to repair and replace the storage cells on the corresponding storage columns where the three target failure points are located in a one-to-one manner.

[0106] Optionally, see Figure 13 , Figure 13 yes Figure 4 In another embodiment of step S330 in the embodiment, the flowchart of step S330 is as follows: step S330 confirms the repair strategy based on the failure direction of each target failure point and further includes the following steps:

[0107] Step S333: In response to the third number being greater than the number of first-direction redundant resources in the redundant storage array, a first sort is performed on the first target failure point having a failure direction in the first direction according to a first number of failed storage cells in the same storage row / column as the first target failure point in the first direction; and according to the result of the first sort, the first-direction redundant resources are used to sequentially repair and replace the storage cells in the corresponding rows / columns of some first target failure points in the preceding sort until the first-direction redundant resources are exhausted.

[0108] The target failure points with a failure direction in the first direction are referred to as first target failure points. When the third number of target failure points with a failure direction in the first direction, i.e., the third number of first target failure points is greater than the number of redundant resources in the first direction in the redundant storage array, i.e., the minimum number of redundant resources in the first direction required to repair all failed storage cells is greater than the number of redundant resources in the first direction in the redundant storage array in practice, in response to the third number being greater than the number of redundant resources in the first direction in the redundant storage array, a first sorting is performed based on a first number of failed storage cells in the same storage row / column as the first target failure point in the first direction. The first sorting refers to sorting the first number of failed storage cells in the same storage row / column as the first target failure point, including the first target failure point, from most to least. Based on the order after the first sorting, redundant resources in the first direction in the redundant storage array are used to sequentially repair and replace storage cells in the corresponding storage rows / columns of the first target failure points that are ranked earlier until the redundant resources in the first direction are exhausted.

[0109] Step S334: Eliminate the failed storage cells in the repaired storage array to update the failed storage cells in the storage array.

[0110] After the storage cells in the corresponding storage row / column where the first target failure point is located are repaired and replaced using the existing redundant resources in the first direction, the number of failed storage cells on the storage columns / rows extending along the second direction in the storage array changes. Therefore, the failed storage cells in the repaired storage array are eliminated from the storage array to update the failed storage cells in the storage array.

[0111] Step S335: Counting the fifth number of failed memory cells in each updated memory column / row extending along the second direction in the memory array, and performing a second sorting.

[0112] A fifth number of failed memory cells in each updated memory column / row extending along the second direction in the memory array is counted and a second sorting is performed, wherein the second sorting is to sort the fifth number of failed memory cells in the memory columns / rows extending along the second direction from most to least.

[0113] Step S336: repairing failed memory cells in memory cells on each memory column / row extending along the second direction in sequence using the second direction redundant resources according to the result of the second sorting, until the second direction redundant resources are exhausted.

[0114] According to the second sorting from most to least according to the number of failed memory cells in the memory cells on each memory column / row extending along the second direction, that is, the memory columns / rows with the largest number of failed memory cells are preferentially selected, and the failed memory cells in the memory cells on each memory column / row extending along the second direction are repaired in sequence using the redundant resources in the second direction until the redundant resources in the second direction are exhausted.

[0115] Optionally, see Figure 14 , Figure 14 yes Figure 4 Another embodiment of step S330 in the embodiment is a flowchart of another embodiment. Step S330 confirms the repair strategy based on the failure direction of each target failure point, including the following steps:

[0116] Step S337: In response to the fourth number being greater than the number of second-direction redundant resources in the redundant storage array, a third sorting is performed on the second target failure points having a failure direction in the second direction according to the second number of failed storage cells in the same storage column / row as the second target failure points in the second direction; and according to the result of the third sorting, the second-direction redundant resources are used to sequentially repair and replace the storage cells in the corresponding storage columns / rows where some of the second target failure points in the earlier sorting are located, until the second-direction redundant resources are exhausted.

[0117] The target failure points with a failure direction in the second direction are referred to as second target failure points. When a fourth number of target failure points with a failure direction in the second direction is greater than the number of redundant resources in the second direction in the redundant memory array, that is, the minimum number of redundant resources in the second direction required to repair all failed memory cells is greater than the actual number of redundant resources in the second direction, in response to the fourth number being greater than the number of redundant resources in the second direction in the redundant memory array, a third sorting is performed based on a second number of failed memory cells in the second direction that are located in the same storage column / row as the second target failure point. The third sorting refers to sorting the second number of failed memory cells, including the second target failure point, that are located in the same storage column / row as the second target failure point from most to least. Based on the order after the third sorting, redundant resources in the second direction are used to sequentially repair and replace memory cells in the storage columns / rows corresponding to some of the second target failure points that are located earlier in the sorting until the redundant resources in the second direction are exhausted.

[0118] Step S338: Eliminate the failed storage cells in the repaired storage array to update the failed storage cells in the storage array.

[0119] After the storage cells in the corresponding storage column / row where the second target failure point is located are repaired and replaced using the existing redundant resources in the second direction, the number of failed storage cells on the storage rows / columns extending along the first direction in the storage array changes. Therefore, the failed storage cells in the repaired storage array are eliminated from the storage array to update the failed storage cells in the storage array.

[0120] Step S339: Counting the sixth number of failed memory cells in the updated memory cells in each storage row / column extending along the first direction in the memory array, and performing a fourth sorting.

[0121] A sixth number of failed memory cells in each updated memory row / column extending along the first direction in the memory array is counted and a fourth sorting is performed. The fourth sorting is to sort the sixth number of failed memory cells in the memory rows / columns extending along the first direction from most to least.

[0122] Step S340: repairing failed memory cells in memory cells on each storage row / column extending along the first direction in sequence using the first direction redundant resources according to the result of the fourth sorting, until the first direction redundant resources are exhausted.

[0123] A fourth sorting is performed based on the number of failed storage cells in the storage cells on each storage row / column extending along the first direction, from most to least, that is, the storage rows / columns with a large number of failed storage cells are preferentially selected, and the failed storage cells in the storage cells on each storage row / column extending along the first direction are repaired in sequence using the redundant resources in the first direction until the redundant resources in the first direction are exhausted.

[0124] Optionally, see Figure 15 , Figure 15 FIG. 1 is a flow chart of another embodiment of the method for repairing a storage device provided by the present application. Figure 15As shown, the position information of all failed storage cells in the storage array is obtained, and the position information in the first direction and the position information in the second direction are combined into a first set and a second set to form a bipartite graph. Based on the bipartite graph, the maximum matching target failure point for eliminating all failed storage cells is obtained, the failure direction of each target failure point is determined, and the third number of first target failure points with a failure direction in the first direction is counted, and the fourth number of second target failure points with a failure direction in the second direction is counted, that is, the minimum number of redundant resources in the first direction and the minimum number of redundant resources in the second direction required to eliminate all failed storage cells. The third number is compared with the actual number of redundant resources in the first direction, and the fourth number is compared with the actual number of redundant resources in the second direction. If the third number is less than the actual number of redundant resources in the first direction, and the fourth number is less than the actual number of redundant resources in the second direction, the third number of redundant resources in the first direction are used to replace the storage rows / columns where the first target failure points are located, and the fourth number of redundant resources in the second direction are used to replace the storage columns / rows where the second target failure points are located. If the third number is greater than the actual number of redundant resources in the first direction, the number of failed storage cells at the first target failure point in the first direction is sorted from most to least, and the storage rows / columns corresponding to the first target failure point are repaired and replaced using the redundant resources in the first direction according to the sorting order until the redundant resources in the first direction are used up, and the failed storage cells of the storage array are updated, and the failed storage cells on the storage columns / rows extending along the second direction are sorted from most to least, and the redundant resources in the second direction are repaired and replaced using the redundant resources in the second direction according to the sorting order until the redundant resources in the second direction are consumed, or the number of failed storage cells in the storage array is zero. If the fourth number is greater than the actual number of redundant resources in the second direction, the number of failed storage cells at the second target failure point in the second direction is sorted from most to least, and the storage columns / rows corresponding to the second target failure point are repaired and replaced using the redundant resources in the second direction according to the sorting order until the redundant resources in the second direction are used up, and the failed storage cells of the storage array are updated, and the failed storage cells on the storage rows / columns extending along the first direction are sorted from most to least, and the redundant resources in the first direction are repaired and replaced using the redundant resources in the first direction according to the sorting order until the redundant resources in the first direction are consumed, or the number of failed storage cells in the storage array is zero.

[0125] This application also provides a storage device repair system, see Figure 16 , Figure 16 FIG. 1 is a structural diagram of an embodiment of a repair system for a storage device provided by the present application. Figure 16As shown, the repair system 10 includes a main control device 110 and a storage device 120. The main control device 110 is used to execute the repair method of any of the above embodiments to generate repair replacement information. The storage device 120 is coupled to the main control device 110 and receives the repair replacement information. The storage device 120 includes a storage grain 121, and the storage grain 121 includes at least one storage block (not marked in the figure), and each storage block includes a storage array (not marked in the figure) and a redundant storage array (not marked in the figure). It can be understood that the main control device 110 is used to execute the repair method of any of the above embodiments to generate repair replacement information, and the storage device 120 receives the repair replacement information to use the redundant resources of the redundant storage array to repair and replace the failed storage unit in the storage array.

[0126] The storage device repair system 10 provided in the present application is provided with a main control device 110 and a storage device 120, wherein the main control device 110 is used to execute the repair method of any of the above embodiments to generate repair replacement information, and the storage device 120 repairs the failed storage unit in the storage array based on the repair replacement information. That is, the main control device 110 obtains the position information of the failed storage unit in the storage array, and constructs a first set whose set elements are the first-direction position information of the failed storage unit and a second set whose set elements are the second-direction position information of the failed storage unit based on the position information of the failed storage unit, and constructs a bipartite graph about the position information of the failed storage unit based on the first set and the second set. Finally, a target failure point of the maximum match of the bipartite graph is obtained based on the bipartite graph, and a repair strategy is confirmed based on the target failure point. That is, the minimum redundant resources required for repairing the failed storage unit of the storage array are determined based on the position information of the target failed storage unit, and the repair strategy is confirmed based on the minimum redundant resources required for repairing the storage array, so as to improve the utilization rate of redundant resources, thereby improving the repair rate of the failed storage units in the storage array, and further improving the product pass rate of the storage device 120.

[0127] In other embodiments, see Figure 17 , Figure 17 yes Figure 16 A structural diagram of another embodiment of the storage device in the embodiment is shown as follows: Figure 17 As shown, the storage device 120 further includes a control die 122, which is connected to the storage die 121 and coupled to the master device 110. The control die 122 and the storage die 121 are packaged together. The control die 122 is configured to receive repair and replacement information. Specifically, the control die 122 receives the repair and replacement information generated by the master device 110 and, based on the repair and replacement information, repairs and replaces failed storage cells in the storage array using redundant resources of the redundant storage array.

[0128] In this embodiment, a control die 122 is provided in the storage device 120 so that the storage device 120 can repair the failed storage cells in the storage array according to the changes of the failed storage cells in the storage array.

[0129] In other embodiments, the repair method and repair system of the present invention can be applied to the test phase of the storage device 120, such as the CP (Chip Probe) test phase. In this embodiment, the main control device 110 can be implemented by the host computer of the test machine, which executes any one of the repair methods in the aforementioned repair method embodiments to generate repair replacement information for use in repairing failed storage units when the storage device 120 is operating normally after leaving the factory.

[0130] The above description is only an implementation method of the present application and does not limit the scope of the patent application. Any equivalent structure or equivalent process transformation made according to the contents of the description and drawings of this application, or directly or indirectly applied in other related technical fields, are also included in the scope of patent protection of this application.

Claims

1. A method for repairing a storage device, characterized in that: The storage device includes a storage array and a redundant storage array, wherein the redundant storage cells in the redundant storage array are used to repair and replace failed storage cells in the storage array, and the repair method includes: obtaining position information of the failed storage cells in the storage array, wherein the position information includes first direction position information and second direction position information; Based on the position information of the failed storage unit, construct a first set and a second set, and construct a bipartite graph, wherein the first set is a set of the position information of the failed storage unit in a first direction, and the second set is a set of the position information of the failed storage unit in a second direction; Obtaining a maximum matching target failure point of the bipartite graph, and confirming a repair strategy based on the target failure point; The step of obtaining a maximum matching target failure point of the bipartite graph and confirming a repair strategy based on the target failure point includes: Obtaining a target failure point of a maximum match of the bipartite graph; Traversing the target failure points and confirming the failure direction of each target failure point; Determining a repair strategy based on the failure direction of each target failure point; The step of obtaining the maximum matching target failure point of the bipartite graph includes: sorting the first elements in the first set and sorting the second elements in the second set; The first elements in the first set are sequentially searched for their matching second elements in the second set according to the association path, and the first element and the matching second element constitute the target failure point, wherein the association path represents the first direction position information and the second direction position information of the failed storage unit corresponding to the first element and the second element.

2. The repair method according to claim 1, characterized in that: The step of sequentially searching for a matching second element in the second set for each first element in the first set according to a valid path, and forming the target failure point with the first element and the matching second element, includes: searching for a temporary matching second element in the second set for the current first element in the first set according to an associated path, wherein the temporary matching second element is a second element in the second set that has an associated path with the current first element and ranks first; Determine whether the temporary matching second element of the current first element is the temporary matching second element of the previous first element; In response to the temporary matching second element of the current first element being the temporary matching second element of the previous first element, determining whether the temporary matching second element is the only matching second element of the previous first element; In response to the temporary matching second element not being the only matching second element for the preceding first element, searching for another temporarily matching second element in the second set that is ranked before the preceding first element according to the association path to serve as an updated temporary matching second element of the preceding first element, wherein the updated temporary matching second element is the first second element in the second set that has an association path with the preceding first element after the temporary matching second element; Update the next first element sorted in the first set as the current first element, and repeat the steps of searching for a temporary matching second element in the second set for the current first element in the first set according to the association path, wherein the temporary matching second element is the second element in the second set that has an association path with the current first element and is sorted first, and subsequent steps, until all first elements in the first set have found a temporary matching second element, and the temporary matching second element of any first element is different from the temporary matching second elements of other first elements, and the temporary matching second elements are respectively used as the matching second elements of the corresponding first elements.

3. The repair method according to claim 2, characterized in that: The method sequentially searches for the matching second element in the second set according to the valid path for the first element in the first set, and uses the first element and the matching second element to constitute the target failure point. It also includes: in response to the temporary matching second element being the only matching second element of the previous first element, searching for other temporary matching second elements in the second set that are ranked before the current first element according to the associated path as the updated temporary matching second element of the current first element, wherein the updated temporary matching second element is the first second element in the second set that has an associated path with the current first element after the temporary matching second element.

4. The repair method according to claim 1, characterized in that: The traversing the target failure points and confirming the failure direction of each target failure point includes: Determine a first number of failed storage cells in a first direction that are in the same storage row / column as a current target failure point, wherein the first number of failed storage cells includes the current target failure point; Determine a second number of failed memory cells in a second direction that are in the same storage column / row as the current target fail point, wherein the second number of failed memory cells includes the current target fail point; determining a failure direction of the current target failure point based on the first number and the second number; Update the next target failure point to the current target failure point, and repeat the steps of confirming the first number of failed storage cells in the same storage row / column as the current target failure point in the first direction, wherein the first number of failed storage cells includes the current target failure point and subsequent steps, so as to traverse all the target failure points and confirm the failure direction of each target failure point.

5. The repair method according to claim 4, characterized in that: The determining the failure direction of the current target failure point based on the first number and the second number includes: in response to the first number being greater than the second number, determining the failure direction of the current target failure point to be a first direction corresponding to the first number; or in response to the first number being smaller than the second number, determining the failure direction of the current target failure point to be a second direction corresponding to the second number; Alternatively, in response to the first number being equal to the second number, the failure direction of the current target failure point is determined to be one of the first direction or the second direction.

6. The repair method according to claim 1, characterized in that: Determining the repair strategy based on the failure direction of each target failure point includes: counting a third number of target failure points having a failure direction in the first direction, and counting a fourth number of target failure points having a failure direction in the second direction, based on the failure direction of each target failure point; In response to the third number being not greater than the number of first-direction redundant resources in the redundant storage array and the fourth number being not greater than the number of second-direction redundant resources in the redundant storage array, according to the failure direction of each target failure point, the first-direction redundant resources and / or the second-direction redundant resources corresponding to the failure direction are used to repair and replace the storage cells in the corresponding storage row / column where each target failure point is located.

7. The repair method according to claim 6, characterized in that: Repairing and replacing the storage unit of the corresponding storage row / column where each target failure point is located by using the first-direction redundant resources and / or the second-direction redundant resources corresponding to the failure direction according to the failure direction of each target failure point, including: in response to the failure direction of the current target failure point being the first direction, repairing and replacing the storage unit of the corresponding storage row / column where the current target failure point is located by using the first-direction redundant resources of a redundant storage row / column; Alternatively, in response to the failure direction of the current target failure point being the second direction, a redundant storage column / row second direction redundant resource is used to repair and replace the storage unit of the storage column / row corresponding to the current target failure point.

8. The repair method according to claim 6, characterized in that: The confirming of the repair strategy based on the failure direction of each target failure point further includes: in response to the third number being greater than the number of redundant resources in a first direction in the redundant storage array, performing a first sorting on the first target failure point having a failure direction in the first direction according to a first number of failed storage cells in the first direction that are located in the same storage row / column as the first target failure point, and sequentially repairing and replacing storage cells in the storage row / column corresponding to some of the first target failure points in the first sorting order using the redundant resources in the first direction according to the result of the first sorting, until the redundant resources in the first direction are exhausted; Eliminating the repaired failed storage cells in the storage array to update the failed storage cells in the storage array; Counting a fifth number of failed memory cells in each updated memory column / row extending along the second direction in the memory array, and performing a second sorting; According to the result of the second sorting, the second-directional redundant resources are used to sequentially repair failed storage cells in the storage cells on each storage column / row extending along the second direction until the second-directional redundant resources are exhausted.

9. The repair method according to claim 6, characterized in that: The determining of the repair strategy based on the failure direction of each target failure point further includes: in response to the fourth number being greater than the number of redundant resources in the second direction in the redundant storage array, performing a third sorting on the second target failure points having a failure direction in the second direction according to a second number of failed storage cells in the second direction that are located in the same storage column / row as the second target failure point, and sequentially repairing and replacing storage cells in the storage column / row corresponding to some of the second target failure points that are ranked earlier according to the result of the third sorting using the redundant resources in the second direction until the redundant resources in the second direction are exhausted; Eliminating the repaired failed storage cells in the storage array to update the failed storage cells in the storage array; Counting a sixth number of failed storage cells in the updated storage cells in each storage row / column extending along the first direction in the storage array, and performing a fourth sorting; According to the result of the fourth sorting, the first-direction redundant resources are used to sequentially repair failed storage cells in storage cells on each storage row / column extending along the first direction until the first-direction redundant resources are exhausted.

10. A storage device repair system, characterized in that: include: A main control device, executing the repair method according to any one of claims 1 to 9 to generate repair replacement information; A storage device is coupled to the main control device, wherein the storage device includes: a storage chip including at least one storage block, each of the storage blocks including a storage array and a redundant storage array.

11. The repair system according to claim 10, characterized in that: The storage device further includes a control die packaged together with the storage die, wherein the control die receives the repair and replacement information.

Images