Faulty word line and faulty bit line information in error correction code
By introducing defect diagram circuits into memory devices to identify faulty word lines and bit lines, and using error correction code system to configure decoding operations, the reading error problem caused by faults is solved, the bit error rate and delay are reduced, and data reading is improved accuracy.
Patent Information
- Application Number
- CN201810895060.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2017-09-08
- Filing Date
- 2018-08-08
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2038-08-08
AI Technical Summary
Failed word lines and faulty bit lines in memory devices may cause multiple memory reading errors, affecting the original bit error rate (RBER). It is difficult for the existing technology to effectively identify and handle these faults, resulting in an increase in error correction code delay and bit error rate. .
An error correction code system was designed to identify fault word lines and bit lines through defect diagram circuits, and use fault bit information to configure decoding operations, including erasing fault bits or trying multiple decoding combinations, to adapt to different error correction code types, such as LDPC , Reed-Solomon and BCH error correction codes to reduce decoding delay and reduce bit error rate.
Effectively identifying and processing fault bit lines reduces the delay of error correction codes, reduces the original bit error rate (RBER), and improves the accuracy and reliability of data reading of memory devices.
Smart Images

Figure CN109473141B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to error correction codes, and more particularly to failed word line and failed bit line information in error correction codes. Background Art
[0002] A memory device may include a plurality of memory cells accessed via a plurality of word lines (WLs) and a plurality of bit lines (BLs). Each WL and each BL is associated with a plurality of memory cells. Therefore, a faulty WL and / or a faulty BL may result in a plurality of memory read errors and thus may adversely affect the raw bit error rate (RBER) of the memory device. BRIEF DESCRIPTION OF THE DRAWINGS
[0003] Features and advantages of the claimed subject matter will be apparent from the following detailed description of embodiments consistent with the claimed subject matter, which description should be considered with reference to the accompanying drawings, in which:
[0004] Figure 1A A functional block diagram of a system including a memory device and a defect map circuit consistent with several embodiments of the present disclosure is shown;
[0005] Figure 1B Shows the corresponding Figure 1A an example tile of any tile of a memory device of;
[0006] Figure 2A and Figure 2B is a flow chart of defect map operations according to various embodiments of the present disclosure; and
[0007] Figure 3 is a flow chart of an error correction operation according to various embodiments of the present disclosure.
[0008] Although the following detailed description will be made with reference to illustrative embodiments, many alternatives, modifications and variations thereof will be apparent to those skilled in the art. DETAILED DESCRIPTION
[0009] The error correction circuit can be configured to encode data bits (information to be stored) with multiple parity bits into a codeword. The parity bits are configured to facilitate decoding of the codeword to recover the data bits in the presence of one or more bit errors. The encoding may conform to and / or be compatible with the selected error correction code. The codeword may then be stored in a memory device. Multiple bits of the codeword may be distributed across the memory device. In other words, the multiple bits included in the codeword may not share a word line (WL) or a bit line (BL).
[0010] In response to a read request, a codeword may be retrieved from the memory device. The error correction circuit may then be configured to decode the codeword to recover the data bits. Due to non-ideal characteristics of the memory device, the retrieved codeword may include one or more erroneous bits. For example, a faulty WL and / or a faulty BL may result in multiple bit errors ("faulty bits") distributed across multiple codewords. Thus, decoding may include detection and / or correction of one or more erroneous bits.
[0011] In general, the present disclosure relates to fault WL and fault BL information in an error correction code. An apparatus, method and / or system may be configured to identify a fault WL and / or a fault BL and include a fault WL identifier and / or a fault BL identifier in a defect map. Then, the apparatus, method and / or system may be configured to use the defect map to inform the error correction circuit which bits (if any) in the codeword are fault bits. The fault bit may be a bit associated with a fault WL and / or a fault BL. Then, the error correction circuit may be configured to configure a decoding operation using the fault bit information. The configuration of the decoding operation may be related to the selected error correction code, as will be described in more detail below. In one example, the fault bit may be erased, thereby reducing the delay associated with the decoding operation. In another example, the error correction circuit may be configured to perform multiple decoding attempts. The number of decoding attempts may be related to the number of fault bits in the codeword. The number of attempts may correspond to at least a portion of all possible value combinations of the fault bit.
[0012] Therefore, a defect map including identifiers corresponding to a failed WL and / or a failed BL can be utilized to facilitate codeword decoding and error correction operations. Erasing failed bits can improve the latency of error correction codes that can accommodate erasures. Identifying failed bits can reduce the raw bit error rate (RBER) by facilitating decoding of error correction codes that cannot accommodate erasures.
[0013] Figure 1A 1 shows a functional block diagram of a system 100 including a defect map circuit consistent with several embodiments of the present disclosure. The system 100 may correspond to and / or be included in a mobile phone, including but not limited to a smart phone (e.g., based on Phone number, based on Phone, based on phones, etc.); wearable devices (e.g., wearable computers, "smart" watches, smart glasses, smart clothing, etc.) and / or systems; computing systems (e.g., servers, workstation computers, desktop computers, laptop computers, tablet computers (e.g., etc.), ultra portable computers, ultra mobile computers, netbook computers and / or sub-notebook computers; etc.
[0014] System 100 includes processor circuit 102, memory controller 104, and memory device 106. For example, processor circuit 102 may correspond to a single-core or multi-core general-purpose processor, such as a processor comprising Those provided by Intel® Corporation, etc. Memory controller 104 may be coupled to and / or included in processor circuit 102 , and may be configured to couple processor circuit 102 to memory device 106 .
[0015] The memory device 106 may include a non-volatile memory, for example, a storage medium that does not require power to maintain the state of data stored by the storage medium. The non-volatile memory may include, but is not limited to, NAND flash memory (e.g., triple-level cell (TLC) NAND or any other type of NAND (e.g., single-level cell (SLC), multi-level cell (MLC), quad-level cell (QLC), etc.), NOR memory, solid-state memory (e.g., planar or three-dimensional (3D) NAND flash memory or NOR flash memory), a storage device using a chalcogenide phase change material (e.g., chalcogenide glass), a byte-addressable non-volatile memory device, a ferroelectric memory, a silicon oxide-nitride-oxide-silicon (SONOS) memory, a polymer memory (e.g., a ferroelectric polymer memory), a byte-addressable random access 3D NAND flash memory, and a byte-addressable random access 3D NAND flash memory. D cross point memory, ferroelectric transistor random access memory (Fe-TRAM), magnetoresistive random access memory (MRAM), phase change memory (PCM, PRAM), resistive memory, ferroelectric memory (F-RAM, FeRAM), spin transfer torque memory (STT), thermal assisted switching memory (TAS), millipede memory, floating junction gate memory (FJGRAM), magnetic tunnel junction (MTJ) memory, electrochemical battery (ECM) memory, binary oxide filament cell memory, interface switching memory, battery-backed RAM, bidirectional memory, nanowire memory, electrically erasable programmable read-only memory (EEPROM), etc. In some embodiments, the byte-addressable random accessible 3D cross point memory may include a transistor-free stackable cross point architecture, in which memory cells are located at the intersection of word lines and bit lines and are individually addressable, and in which bit storage is based on changes in body resistance.
[0016] The processor circuit 102 may be configured to provide memory access requests, such as write requests and / or read requests, to the memory controller 104. For example, the read request may include address information of data to be read from a memory location corresponding to the address information in the memory device 106. The memory controller 104 may then be configured to manage reading the data from the memory device 106.
[0017] The memory controller 104 includes a memory controller control circuit 110, an error correction circuit 112, a defect map circuit 114, and a memory device map 116. The memory controller control circuit 110 is configured to determine the address of the target memory cell in response to a memory access request from the processor circuit 102. The memory controller control circuit 110 is also configured to identify the WL and BL corresponding to the address of the target memory cell based at least in part on the determined address and at least in part on the memory device map 116. The memory device map 116 is configured to associate the memory cell address with the WL identifier and the BL identifier. Therefore, the memory device map 116 may include an array of addresses, wherein each address is associated with a corresponding WL identifier and a corresponding BL identifier corresponding to the memory cell associated with the address. The memory controller control circuit 110 is also configured to select the target memory cell and write to the selected target memory cell or read from the selected target memory cell. Selecting, writing, and / or reading may include driving the identified WL and / or the identified BL to accommodate the memory access operation.
[0018] The memory controller control circuit 110 is configured to receive data to be written to the memory device 106 from the processor circuit 102, for example, in response to a write request. Then, the memory controller control circuit 110 may be configured to provide the data to be written to the error correction circuit 112. The error correction circuit 112 may be configured to encode the data to be written using an error correction code to generate a corresponding codeword. Therefore, the codeword may include a plurality of data bits and a plurality of error correction bits. The data bit corresponds to the information bit, and the error correction bit corresponds to the parity bit. In one embodiment, the error correction code may conform to a low-density parity check (LDPC) error correction code and / or be compatible with a low-density parity check (LDPC) error correction code. In another embodiment, the error correction code may conform to a Reed-Solomon error correction code and / or be compatible with a Reed-Solomon error correction code. In another embodiment, the error correction code may conform to a Bose-Chaudhuri-Hocquenghem (BCH) error correction code and / or be compatible with a Bose-Chaudhuri-Hocquenghem (BCH) error correction code.
[0019] The memory controller control circuit 110 may then be configured to store the corresponding codeword in the memory device 106. The memory controller control circuit 110 may be configured to read the codeword in response to the read request and provide the received codeword to the error correction circuit 112. The error correction circuit 112 may then be configured to decode the received codeword.
[0020] The memory device 106 includes a plurality of dies, D1, ..., Dn. Each die (e.g., D1) includes a plurality of partitions P1, ..., Pq. Each partition (e.g., partition P1) includes a plurality of slices S1, ..., Sn. Each slice (e.g., slice S1) includes a plurality of tiles T1, ..., Tm. In a non-limiting example, each die (e.g., die D1) may include 32 partitions; each partition (e.g., partition P1) may include four slices; and each slice (e.g., slice S1) may include 128 tiles. The values n, q, and m may be integers greater than or equal to 1.
[0021] Figure 1B Shows the corresponding Figure 1A An example tile 150 of any tile T1, ..., Tm of a memory device 106. The example tile 150 includes two deck pairs 152-1, 152-2. In other examples, the tiles may include more or fewer deck pairs. Each deck pair (e.g., deck pair 152-1) includes a first plurality of word lines (WL) WL00, WL01, ..., WL0N, a second plurality of word lines WL10, WL11, ..., WL1N, a plurality of bit lines (BL) BL0, BL1, ..., BLM, and a plurality of memory cells (e.g., memory cell 156). Each WL may cross a BL at a memory cell (e.g., memory cell 156). For example, a first plurality of WLs WL00, WL01, ..., WL0N, a plurality of BLs BL0, BL1, ..., BLM and a corresponding plurality of memory cells may correspond to a first card stack, and a second plurality of WLs WL10, WL11, ..., WL1N, a plurality of BLs BL0, BL1, ..., BLM and a corresponding plurality of memory cells may correspond to a second card stack of the card stack pair 152-1. Thus, each card stack 152-1, 152-2 may include a memory cell array, and the memory device 106 may include multiple card stacks. In a non-limiting example, each tile (e.g., tile 150) may include 4000 WLs and 2000 BLs in four card stacks.
[0022] Turn again Figure 1A, the defect map circuit 114 includes a defect map logic 120, a defect map 122, a defect map circuit memory 124, and WL / BL bit error data 126. The defect map logic 120 is configured to generate and / or update the defect map 122 to provide the defect map information to the error correction circuit 112 and update the WL / BL bit error data 126, which will be described in more detail below. The defect map circuit memory 124 can be configured to contain the defect map 122 and / or the WL / BL bit error data 126. The defect map 122 is configured to contain the WL and / or BL identifiers of each WL and / or each BL that has been identified as a fault. The WL / BL bit error data 126 is configured to contain the following bit error data, which can then be used by the defect map logic 120 to identify a faulty WL and / or a faulty BL. The WL / BL bit error data 126 can be configured to store the bit error data of the WL and / or BL having a raw bit error rate (RBER) less than a threshold RBER. If the corresponding RBER increases to be equal to or greater than a threshold RBER, such that the associated WL and / or the associated BL is identified as faulty, the corresponding bit error data may be deleted.
[0023] In operation, in response to a read request from the processor circuit 102, the memory controller control circuit 110 may be configured to read a codeword from the memory device 106. For example, the memory controller control circuit 110 may receive address information corresponding to the address of the data to be read. Then, the memory controller control circuit 110 may be configured to determine the address. Then, the memory controller control circuit 110 may be configured to utilize the memory device map 116 to identify each WL and each BL associated with the address. It can be appreciated that an address corresponding to a codeword may be associated with multiple bits. One or more bits may be stored in each of a plurality of memory cells. Then, the memory cells may be distributed across the memory device 106. In one example, the memory cells may be randomly distributed across the memory device 106. In another example, each memory cell may be located in the same corresponding position in each tile of a plurality of tiles in a partition. Other distributions of memory cells for stored codewords are also contemplated herein.
[0024] The memory controller control circuit 110 may then be configured to provide the codeword to the error correction circuit 112. The error correction circuit 112 may not know the location of the bits of the received codeword in the memory device 106. The defect map logic 120 may then be configured to retrieve or receive the address of the codeword. The address may be provided by or retrieved from the memory controller control circuit 110.
[0025] The defect map logic 120 may then be configured to identify a corresponding WL and a corresponding BL for each bit in the codeword. For example, the defect map logic 120 may be configured to access the memory device map 116 and identify each corresponding WL and corresponding BL associated with the address. The defect map logic 120 may then be configured to determine whether any identified WL and / or any identified BL is faulty. For example, the defect map logic 120 may be configured to access the defect map 122 to make the determination.
[0026] The defect map 122 is configured to include a WL identifier corresponding to a failed WL and / or a BL identifier corresponding to a failed BL. The defect map logic 120 may be configured to determine whether a WL identifier corresponding to any identified WL and / or a BL identifier corresponding to any identified BL is included in the defect map 122. If the defect map 122 includes a WL identifier corresponding to an identified WL and / or a BL identifier corresponding to an identified BL, the defect map logic 120 may be configured to notify the error correction circuit 112. The notification is configured to include a corresponding bit identifier for each bit (i.e., a "failure bit") of the codeword associated with the identified failed WL and / or the identified failed BL. Thus, the error correction circuit 112 may be provided with a corresponding identifier for each failed bit included in the codeword.
[0027] If the error correction circuit 112 is provided with a notification of a faulty bit, the error correction circuit 112 may configure the decoding operation based at least in part on the selected error correction code. In other words, the error correction circuit 112 may be configured to implement one or more error correction codes. Error correction codes may include, but are not limited to, LDPC, Reed-Solomon (RS), BCH, etc. It may be appreciated that different error correction codes may have different characteristics and / or different capabilities. For example, LDPC and / or Reed-Solomon may manage erasures. Erasures correspond to bits that cannot be read due to a fault in a memory device, such as a faulty WL and / or a faulty BL. LDPC and / or Reed-Solomon may utilize the "cognition" of the corresponding bit position of each erasure in a codeword to speed up the decoding process and thus reduce delays. In another example, BCH may not be able to successfully decode a codeword in the presence of an erasure. Thus, in one example, if the error correction code complies with and / or is compatible with LDPC or Reed-Solomon error correction codes, the error correction circuit 112 may configure the decoding operation by erasing the failed bits.
[0028] In another example, if the error correction code conforms to and / or is compatible with the BCH error correction code, the error correction circuit 112 may configure the decoding operation to attempt to decode the codeword using at least a portion of a plurality of possible values of the fault bit. For example, if the codeword includes two fault bits, the error correction circuit 112 may configure the decoding operation to attempt to decode the codeword using four possible combinations of up to two fault bits (i.e., 00, 01, 10, 11). The error correction circuit 112 may then successfully decode the codeword using one combination of values of the fault bits. Successfully decoding the codeword may then not affect the uncorrectable bit error rate (UBER). Therefore, the error correction circuit 112 may then decode the codeword using a decoding operation that has been configured based at least in part on the selected error correction code.
[0029] The error correction circuit 112 is configured to determine whether the codeword contains any error bits that do not correspond to the fault bits. Error bits that do not correspond to the fault bits are error bits that are not related to any identified fault WL or any identified fault BL. If the codeword does contain error bits that do not correspond to the fault bits, the error correction circuit 112 is configured to notify the defect map circuit 114 (i.e., the defect map logic 120). The defect map logic 120 can then be configured to retrieve or receive the corresponding position of each error bit in the decoded codeword. For example, the corresponding position of each error bit can be retrieved from the error correction circuit 112 by the defect map logic 120, or can be provided to the defect map logic 120 by the error correction circuit 112.
[0030] The defect map logic 120 may then be configured to update the WL / BL bit error data 126 for each error bit. As used herein, "WL / BL" corresponds to "WL and / or BL". The WL / BL bit error data 126 is configured to include a WL identifier and corresponding WL bit error data and / or a BL identifier and corresponding BL bit error data for each error bit identified by the error correction circuit 112. The WL / BL bit error data 126 is configured to include a corresponding indicator for each bit associated with the WL identifier or the BL identifier. In other words, for each WL identifier and / or BL identifier, the WL / BL bit error data 126 is configured to include an indicator (e.g., a bit) for each memory cell associated with the WL and / or BL. The indicator is configured to indicate whether the associated bit is identified as an error bit by the error correction circuit 112. The defect map logic 120 is configured to set a bit error indicator for any error bit that has not been set in the WL / BL bit error data.
[0031] Then, the defect map logic 120 may be configured to determine whether the corresponding WL and / or the corresponding BL is faulty using the WL / BL bit error data 126. Whether the corresponding WL and / or the corresponding BL is faulty may be determined based at least in part on the WL bit error data and / or the BL bit error data. Whether the corresponding WL and / or the corresponding BL is faulty may be further determined based at least in part on a threshold RBER. The RBER for the corresponding WL and / or the corresponding BL may be determined as a ratio of the number of error bits to the total number of bits associated with the corresponding WL and / or the corresponding BL. If the RBER for the corresponding WL and / or the corresponding BL is greater than or equal to the corresponding corresponding threshold RBER, the defect map logic 120 may consider the corresponding WL and / or the corresponding BL to be faulty. The threshold RBER may be in the range of 10% (%) to 50%. In a non-limiting example, the threshold RBER may be equal to 30%.
[0032] If the corresponding WL and / or the corresponding BL is faulty, the defect map logic 120 is configured to update the defect map 122. For example, the defect map 122 may be updated by adding a WL identifier corresponding to the faulty WL and / or a BL identifier corresponding to the faulty BL to the defect map 122. If the corresponding WL and / or the corresponding BL is faulty, the defect map logic 120 is configured to update the WL / BL bit error data 126. For example, the WL / BL bit error data 126 may be updated by deleting the WL identifier and the associated WL bit error data of the corresponding faulty WL and / or deleting the BL identifier and the associated BL bit error data of the corresponding faulty BL. Therefore, the storage capacity associated with the WL / BL bit error data 126 may be maintained.
[0033] Therefore, a defect map including identifiers corresponding to a failed WL and / or a failed BL can be utilized to facilitate codeword decoding and error correction operations. Erasing a failed bit can improve the latency of an error correction code that can accommodate erasures. Identifying a failed bit can reduce the RBER by facilitating decoding of an error correction code that cannot accommodate erasures.
[0034] Figure 2A and Figure 2B are flow charts 200 , 250 of defect map operations according to various embodiments of the present disclosure. Figure 2B yes Figure 2A of the continuation, therefore, can be best understood when considered together Figure 2A and Figure 2B In particular, flow charts 200, 250 illustrate identifying faulty WLs and / or BLs, providing error bit information to error correction circuits, and maintaining and updating defect maps. For example, Figure 1A The operations may be performed by elements of the defect map circuit 114 (eg, defect map logic 120).
[0035] The operation of this embodiment may begin at operation 202 by providing a codeword to an error correction circuit. For example, a memory controller control circuit may be configured to read a codeword from a memory device and provide the codeword to an error correction circuit. Operation 204 includes retrieving or receiving an address of the codeword. For example, the address may be received or retrieved from the memory controller control circuit. At operation 206, a WL and a BL may be identified for each bit in the codeword. For example, the identification may be performed using a memory device map. At operation 208, it may be determined, at least in part based on a defect map, whether any identified WL and / or any identified BL is faulty. If an identified WL and / or an identified BL is faulty, the error correction circuit may be notified at operation 210. The program flow may then proceed to operation 212.
[0036] If no WLs are identified and no BLs are identified as being faulty, program flow may proceed to operation 212. It may be determined at operation 212 whether the codeword contains any erroneous bits. For example, the error correction circuitry may be configured to provide an indication to the defect map logic of the presence of erroneous bits, if any, in the codeword. If there are no erroneous bits in the codeword, program flow may continue at operation 214.
[0037] Now turn to Figure 2B , if there is an error bit in the codeword, the corresponding position of each error bit in the decoded codeword can be retrieved or received from the error correction circuit at operation 216. At operation 218, the WL / BL bit error data can be updated for each faulty bit. For example, a bit error indicator can be set for any error bit that has not been set in the WL / BL bit error data. At operation 220, it can be determined whether the corresponding WL and / or the corresponding BL are faulty based at least in part on the WL bit error data and / or the BL bit error data. If the corresponding WL and the corresponding BL are not faulty, then the program flow can continue at operation 222. If the corresponding WL and / or the corresponding BL are faulty, the defect map can be updated at operation 224. The WL bit error data and / or the BL bit error data can be updated at operation 226. Then, the program flow can continue in operation 228.
[0038] Thus, a failed WL and / or a failed BL may be identified, and associated failed bit information may be provided to an error correction circuit. The error correction circuit is configured to utilize the failed bit information to facilitate a decoding operation. The error correction circuit may then provide bit error information, which may then be utilized by the defect map logic to identify a failed WL and / or a failed BL.
[0039] Figure 3300 is a flowchart of error correction operations according to various embodiments of the present disclosure. In particular, flowchart 300 illustrates decoding a codeword based at least in part on an indication of a failed bit provided by defect map logic. For example, Figure 1A The error correction circuit 112 is used to perform the operation.
[0040] The operation of this embodiment may begin with receiving or retrieving a codeword at operation 302. For example, the codeword may be received from a memory controller control circuit or retrieved from a memory controller control circuit. It may be determined at operation 304 whether a notification of a faulty bit has been received from the defect map logic. If a notification of a faulty bit has been received, a decoding operation may be configured at least in part based on the selected error correction code at operation 306. In one example, if the error correction code conforms to and / or is compatible with LDPC or Reed-Solomon code, the faulty bit may be erased. In another example, if the error correction code conforms to and / or is compatible with BCH, the decoding operation may be configured to attempt to decode the codeword using at least a portion of a plurality of possible values of the faulty bit. Then, the program flow may proceed to operation 308. If there is no notification of a faulty bit, the program flow may proceed to operation 308. The codeword may be decoded at operation 308. It may be determined at operation 310 whether the codeword contains any error bits that do not correspond to the faulty bit. If the codeword does not contain any erroneous bits that do not correspond to failed bits, program flow may continue at operation 314. If the codeword does contain erroneous bits that do not correspond to failed bits, the defect map circuit (logic) may be notified at operation 312. Program flow may then proceed to operation 314.
[0041] Thus, decoding operations may be configured based at least in part on the selected error correction code in response to the indication of the failure bit.
[0042] Although Figure 2A , Figure 2B and Figure 3 The flowcharts of the present invention illustrate the operation according to various embodiments, but it should be understood that the present invention is not Figure 2A , Figure 2B and Figure 3 All operations described in are required by other embodiments. In addition, it is fully contemplated herein that in other embodiments of the present disclosure, Figure 2A , Figure 2B and / or Figure 3 The operations depicted in and / or other operations described herein may be combined in ways not specifically shown in any of the figures, and such embodiments may include more Figure 2A , Figure 2B and Figure 3Therefore, claims directed to features and / or operations that are not precisely shown in one drawing are considered to be within the scope and content of the present disclosure.
[0043] As used in any embodiment herein, the term "logic" may refer to an application, software, firmware, and / or circuitry configured to perform any of the above operations. Software may be embodied as a software package, code, instructions, instruction sets, and / or data recorded on a non-transitory computer-readable storage medium. Firmware may be embodied as code, instructions, instruction sets, and / or data hard-coded (e.g., non-volatile) in a memory device.
[0044] "Circuitry" as used in any embodiment herein may include, for example, alone or in any combination, hardwired circuits, programmable circuits such as a computer processor including one or more separate instruction processing cores, state machine circuits, logic and / or firmware storing instructions executed by programmable circuits. The circuit may be embodied as an integrated circuit, such as an integrated circuit chip. In some embodiments, the circuit may be formed at least in part by a processor circuit 102 executing code and / or instruction sets (e.g., software, firmware, etc.) corresponding to the functions described herein, thereby transforming a general-purpose processor into a special-purpose processing environment to perform one or more of the operations described herein. In some embodiments, various components and circuits of the memory controller circuit or other systems may be combined in a system-on-chip (SoC) architecture.
[0045] The foregoing provides example system architectures and methods, however, modifications to the present disclosure are possible. The processor may include one or more processor cores and may be configured to execute system software. The system software may include, for example, an operating system. The device memory may include an I / O memory buffer configured to store one or more data packets to be sent by a network interface or received by a network interface.
[0046] An operating system (OS) may be configured to manage system resources and control tasks running on, for example, system 100. For example, the OS may use or In another example, the OS may use Android™, iOS, or In some embodiments, the OS may be replaced by a virtual machine monitor (or hypervisor), which may provide an abstraction layer for the underlying hardware to various operating systems (virtual machines) running on one or more processing units. The operating system and / or the virtual machine may implement a protocol stack. The protocol stack may execute one or more programs to process packets. An example of a protocol stack is a TCP / IP (Transmission Control Protocol / Internet Protocol) protocol stack, which includes one or more programs for handling (e.g., processing or generating) packets to send and / or receive over a network.
[0047] The defect map circuit memory 124 may include one or more of the following types of memory: semiconductor firmware memory, programmable memory, non-volatile memory, read-only memory, electrically programmable memory, random access memory, memory, magnetic disk memory, and / or optical disk memory. Additionally or alternatively, the system memory may include other and / or later developed types of computer-readable memory.
[0048] Embodiments of the operations described herein may be implemented in a computer-readable storage device having instructions stored thereon, which when executed by one or more processors perform the method. The processor may include, for example, a processing unit and / or a programmable circuit. The storage device may include a machine-readable storage device, which includes any type of tangible, non-transitory storage device, for example, any type of disk, including a floppy disk, an optical disk, a compact disk read-only memory (CD-ROM), a compact disk rewritable (CD-RW), and a magneto-optical disk, a semiconductor device such as a read-only memory (ROM), a random access memory (RAM) such as a dynamic and static RAM, an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic card or an optical card, or any type of storage device suitable for storing electronic instructions.
[0049] In some embodiments, a hardware description language (HDL) may be used to specify circuit and / or logic implementations for various logic and / or circuits described herein. For example, in one embodiment, the hardware description language may conform to or be compatible with Very High Speed Integrated Circuit (VHSIC) Hardware Description Language (VHDL), which may implement semiconductor fabrication of one or more circuits and / or logic described herein. VHDL may conform to or be compatible with IEEE Standard 1076-1987, IEEE Standard 1076.2, IEEE 1076.1, IEEE Draft 3.0 of VHDL-2006, IEEE Draft 4.0 of VHDL-2008, and / or other versions of the IEEE VHDL standard and / or other hardware description standards.
[0050] Example
[0051] Examples of the present disclosure include subject matter such as methods related to failed wordline and failed bitline information in error correction codes, units, devices or apparatuses or systems for performing actions of the methods, as described below.
[0052] Example 1. According to this example, a memory controller is provided. The memory controller includes a memory controller control circuit, a defect map logic, and an error correction circuit. The memory controller control circuit is used to read a codeword from a memory device. The defect map logic is used to identify a corresponding word line (WL) and a corresponding bit line (BL) for each bit in the codeword based at least in part on a memory device map and to determine whether any identified WL and / or any identified BL is faulty based at least in part on the defect map. If any identified WL and / or any identified BL is faulty, the error correction circuit is used to configure a decoding operation.
[0053] Example 2. This example includes elements of Example 1, wherein the defect map logic is used to determine whether the WL and / or BL is faulty based at least in part on corresponding WL bit error data and / or corresponding BL bit error data; and if the WL is faulty and / or the BL is faulty, update the defect map.
[0054] Example 3. This example includes elements of Example 2, wherein determining whether the WL and / or the BL is faulty comprises determining a raw bit error rate (RBER) for the WL and / or the BL.
[0055] Example 4. This example includes the elements of Example 1 or 2, wherein the error correction circuit is to notify the defect map logic whether the codeword contains an error bit that is not a failure bit associated with the identified WL and / or the identified BL.
[0056] Example 5. This example includes elements of Example 1 or 2, wherein configuring the decoding operation is based at least in part on the selected error correction code.
[0057] Example 6. This example includes elements of Example 5, wherein the error correction code includes a low-density parity check (LDPC) error correction code, a Reed-Solomon error correction code, or a Bose-Chaudhuri-Hocquenghem (BCH) error correction code.
[0058] Example 7. This example includes elements of Example 5, wherein the selected error correction code is LDPC or Reed-Solomon, and the error correction circuit is used to erase each failed bit of the codeword, each failed bit being associated with an identified failed WL and / or an identified failed BL.
[0059] Example 8. This example includes elements of Example 5, wherein the selected error correction code is BCH, and the error correction circuit is used to attempt to decode the codeword using at least a portion of a plurality of possible values of one or more failure bits of the codeword, each failure bit being associated with an identified failure WL and / or an identified failure BL.
[0060] Example 9. This example includes elements of Example 2, wherein the defect map logic is to update the WL bit error data if the WL is faulty and / or to update the BL bit error data if the BL is faulty.
[0061] Example 10. This example includes elements of Example 1 or 2, wherein a plurality of bits in the codeword are distributed across a memory device.
[0062] Example 11. According to this example, a method is provided. The method includes controlling, by a memory controller, circuitry to read a codeword from a memory device; identifying, by a defect map logic, a corresponding word line (WL) and a corresponding bit line (BL) for each bit in the codeword based at least in part on a memory device map; determining, by the defect map logic, at least in part on a defect map, whether any identified WL and / or any identified BL is faulty; and configuring a decoding operation by an error correction circuit if any identified WL and / or any identified BL is faulty.
[0063] Example 12. This example includes elements of Example 11, further comprising: determining, by the defect map logic, whether the WL and / or the BL is faulty based at least in part on corresponding WL bit error data and / or corresponding BL bit error data; and, if the WL is faulty and / or the BL is faulty, updating the defect map by the defect map logic.
[0064] Example 13. This example includes elements of Example 12, wherein determining whether the WL and / or the BL is faulty comprises determining a raw bit error rate (RBER) for the WL and / or the BL.
[0065] Example 14. This example includes the elements of Example 11, further comprising: notifying the defect map logic, by the error correction circuit, whether the codeword contains an error bit, the error bit not being a failure bit associated with the identified WL and / or the identified BL.
[0066] Example 15. This example includes elements of Example 11, wherein the configuration is based at least in part on the selected error correction code.
[0067] Example 16. This example includes elements of Example 15, wherein the error correction code includes a low-density parity check (LDPC) error correction code, a Reed-Solomon error correction code, or a Bose-Chaudhuri-Hocquenghem (BCH) error correction code.
[0068] Example 17. This example includes elements of Example 15, wherein the selected error correction code is LDPC or Reed-Solomon, and the error correction circuit is used to erase each failed bit of the codeword, each failed bit being associated with an identified failed WL and / or an identified failed BL
[0069] Example 18. This example includes the elements of Example 15, wherein the selected error correction code is BCH, and the error correction circuit attempts to decode the codeword using at least a portion of a plurality of possible values of one or more failure bits of the codeword, each failure bit being associated with an identified failure WL and / or an identified failure BL.
[0070] Example 19. This example includes the elements of Example 12, further comprising: updating, by the defect map logic, the WL bit error data if the WL is faulty and / or updating the BL bit error data if the BL is faulty.
[0071] Example 20. This example includes elements of Example 11, wherein a plurality of bits in the codeword are distributed across a memory device.
[0072] Example 21. According to this example, a system is provided. The system includes a memory device and a memory controller. The memory controller includes a memory controller control circuit, a defect map logic, and an error correction circuit. The memory controller control circuit is used to read a codeword from the memory device. The defect map logic is used to identify the corresponding word line (WL) and the corresponding bit line (BL) for each bit in the codeword based at least in part on the memory device map and determine whether any identified WL and / or any identified BL is faulty based at least in part on the defect map. If any identified WL and / or any identified BL is faulty, the error correction circuit is used to configure a decoding operation.
[0073] Example 22. This example includes elements of Example 21, wherein the defect map logic is used to determine whether the WL and / or BL is faulty based at least in part on corresponding WL bit error data and / or corresponding BL bit error data; and if the WL is faulty and / or the BL is faulty, update the defect map.
[0074] Example 23. This example includes the elements of Example 22, wherein determining whether a WL and / or BL is faulty comprises determining a raw bit error rate (RBER) for the WL and / or BL.
[0075] Example 24. This example includes the elements of Example 21 or 22, wherein the error correction circuit is to notify the defect map logic whether the codeword contains an error bit that is not a failure bit associated with the identified WL and / or the identified BL.
[0076] Example 25. This example includes the elements of Example 21 or 22, wherein configuring the decoding operation is based at least in part on the selected error correction code.
[0077] Example 26. This example includes the elements of Example 25, wherein the error correction code comprises a low-density parity check (LDPC) error correction code, a Reed-Solomon error correction code, or a Bose-Chaudhuri-Hocquenghem (BCH) error correction code.
[0078] Example 27. This example includes elements of Example 25, wherein the selected error correction code is LDPC or Reed-Solomon, and the error correction circuit is used to erase each failed bit of the codeword, each failed bit being associated with an identified failed WL and / or an identified failed BL.
[0079] Example 28. This example includes elements of Example 25, wherein the selected error correction code is BCH, and the error correction circuit is used to attempt to decode the codeword using at least a portion of a plurality of possible values of one or more failure bits of the codeword, each failure bit being associated with an identified failure WL and / or an identified failure BL.
[0080] Example 29. This example includes elements of Example 22, wherein the defect map logic is to update the WL bit error data if the WL is faulty and / or update the BL bit error data if the BL is faulty.
[0081] Example 30. This example includes elements of Example 21 or 22, wherein the plurality of bits in the codeword are distributed across the memory devices.
[0082] Example 31. According to this example, a computer-readable storage device is provided. The device has instructions stored thereon, which, when executed by one or more processors, result in the following operations, including: reading a codeword from a memory device; identifying a corresponding word line (WL) and a corresponding bit line (BL) for each bit in the codeword based at least in part on a memory device map; determining whether any identified WL and / or any identified BL is faulty based at least in part on a defect map; and configuring a decoding operation if any identified WL and / or any identified BL is faulty.
[0083] Example 32. This example includes elements of Example 31, wherein the instructions, when executed by one or more processors, result in the following additional operations, including: determining, by the defect map logic, whether the WL and / or the BL is faulty based at least in part on corresponding WL bit error data and / or corresponding BL bit error data; and, if the WL is faulty and / or the BL is faulty, updating the defect map by the defect map logic.
[0084] Example 33. This example includes elements of Example 32, wherein determining whether the WL and / or the BL is faulty comprises determining a raw bit error rate (RBER) for the WL and / or the BL.
[0085] Example 34. This example includes elements of Example 31 or 32, wherein the instructions, when executed by one or more processors, result in the following additional operations, including: notifying the defect map logic by the error correction circuit whether the codeword contains an error bit, and the error bit is not a fault bit associated with the identified WL and / or the identified BL.
[0086] Example 35. This example includes elements of Example 31 or 32, wherein the configuration is based at least in part on the selected error correction code.
[0087] Example 36. This example includes elements of Example 35, wherein the error correction code comprises a low-density parity check (LDPC) error correction code, a Reed-Solomon error correction code, or a Bose-Chaudhuri-Hocquenghem (BCH) error correction code.
[0088] Example 37. This example includes elements of Example 35, wherein the selected error correction code is LDPC or Reed-Solomon, and the error correction circuit is used to erase each faulty bit of the codeword, each faulty bit being associated with an identified faulty WL and / or an identified faulty BL.
[0089] Example 38. This example includes elements of Example 35, wherein the selected error correction code is BCH, and the error correction circuit is used to attempt to decode the codeword using at least a portion of multiple possible values of one or more failure bits of the codeword, each failure bit being associated with an identified failure WL and / or an identified failure BL.
[0090] Example 39. This example includes the elements of Example 32, wherein the instructions when executed by one or more processors result in the following additional operations including: updating WL bit error data if the WL is faulty and / or updating BL bit error data if the BL is faulty.
[0091] Example 40. This example includes elements of Example 31 or 32, wherein the plurality of bits in the codeword are distributed across the memory devices.
[0092] Example 41. According to this example, a device is provided. The device includes a unit for reading a codeword from a memory device through a memory controller control circuit; a unit for identifying a corresponding word line (WL) and a corresponding bit line (BL) for each bit in the codeword based at least in part on a memory device map through a defect map logic; a unit for determining whether any identified WL and / or any identified BL is faulty based at least in part on the defect map through the defect map logic; and a unit for configuring a decoding operation through an error correction circuit if any identified WL and / or any identified BL is faulty.
[0093] Example 42. This example includes elements of Example 41, further comprising a unit for determining, by defect map logic, whether the WL and / or BL is faulty based at least in part on corresponding WL bit error data and / or corresponding BL bit error data; and a unit for updating the defect map by the defect map logic if the WL is faulty and / or the BL is faulty.
[0094] Example 43. This example includes elements of Example 42, wherein determining whether the WL and / or the BL is faulty comprises determining a raw bit error rate (RBER) for the WL and / or the BL.
[0095] Example 44. This example includes the elements of Example 41 or 42, further comprising means for notifying, by the error correction circuit, the defect map logic whether the codeword contains an erroneous bit that is not a failed bit associated with the identified WL and / or the identified BL.
[0096] Example 45. This example includes elements of Example 41 or 42, wherein the configuration is based at least in part on the selected error correction code.
[0097] Example 46. This example includes the elements of Example 45, wherein the error correction code comprises a low-density parity check (LDPC) error correction code, a Reed-Solomon error correction code, or a Bose-Chaudhuri-Hocquenghem (BCH) error correction code.
[0098] Example 47. This example includes elements of Example 45, wherein the selected error correction code is LDPC or Reed-Solomon, and the error correction circuit is used to erase each failed bit of the codeword, each failed bit being associated with an identified failed WL and / or an identified failed BL.
[0099] Example 48. This example includes elements of Example 45, wherein the selected error correction code is BCH, and the error correction circuit is used to attempt to decode the codeword using at least a portion of a plurality of possible values of one or more failure bits of the codeword, each failure bit being associated with an identified failure WL and / or an identified failure BL.
[0100] Example 49. This example includes the elements of Example 42, further comprising means for updating, by the defect map logic, the WL bit error data if the WL is faulty and / or updating the BL bit error data if the BL is faulty.
[0101] Example 50. This example includes elements of Example 41 or 42, wherein the plurality of bits in the codeword are distributed across the memory devices.
[0102] Example 51. This example includes elements of Example 21 or 22, further comprising a processor circuit.
[0103] Example 52. According to this example, a system is provided. The system includes at least one device, wherein the at least one device is configured to perform the method of any one of Examples 11 to 20.
[0104] Example 53. According to this example, a device is provided. The device includes a unit for performing the method of any one of Examples 11 to 20.
[0105] Example 54. According to this example, a computer-readable storage device is provided. The device stores instructions, which, when executed by one or more processors, result in the following operations, including: the method according to any one of Examples 11 to 20.
[0106] The terms and expressions employed herein are used as terms of description rather than limitation, and in the use of these terms and expressions, there is no intention to exclude any equivalents of the features shown and described (or portions thereof), and it is recognized that various modifications may be made within the scope of the claims. Therefore, the claims are intended to cover all such equivalents.
[0107] Various features, aspects and embodiments have been described herein. As will be appreciated by those skilled in the art, these features, aspects and embodiments are susceptible to being combined with each other and to being varied and modified. Therefore, the present disclosure should be deemed to include such combinations, variations and modifications.
Claims
1. A memory controller, include: A memory controller control circuit for reading a codeword from a memory device; defect map logic to identify a corresponding word line (WL) and a corresponding bit line (BL) for each bit in the codeword based at least in part on a memory device map, and to determine whether any identified WL and / or any identified BL is faulty based at least in part on the defect map; a defect map circuit memory configured to store the defect map and corresponding WL bit error data and / or corresponding BL bit error data; and error correction circuitry for configuring a decoding operation if any identified WL and / or any identified BL is determined to be faulty based on the defect map, wherein the error correction circuit is configured to notify the defect map logic if the codeword contains an error bit that is not a faulty bit stored in the defect map circuit memory and associated with the identified WL and / or the identified BL, And wherein the defect map logic is used to determine whether the WL and / or BL associated with the corresponding WL bit error data and / or the corresponding BL bit error data is faulty based at least in part on the corresponding WL bit error data and / or the corresponding BL bit error data; and if the WL is faulty and / or the BL is faulty, then in the defect map circuit memory, the defect map is updated and the corresponding bit error data is deleted.
2. The memory controller according to claim 1, in, Determining whether the WL and / or the BL is faulty includes determining a raw bit error rate (RBER) for the WL and / or the BL.
3. The memory controller according to claim 1, in, The decoding operation is configured based at least in part on the selected error correction code.
4. The memory controller according to claim 3, in, The error correction code includes a low-density parity check (LDPC) error correction code, a Reed-Solomon error correction code, or a Bose-Chaudhuri-Hocquenghem (BCH) error correction code.
5. The memory controller according to claim 3, in, The selected error correction code is LDPC or Reed-Solomon, and the error correction circuit is used to erase each failed bit of the codeword, each failed bit being associated with an identified failed WL and / or an identified failed BL.
6. The memory controller according to claim 3, in, The selected error correction code is BCH, and the error correction circuit is used to attempt to decode the codeword using at least a portion of a plurality of possible values of one or more failure bits of the codeword, each failure bit being associated with an identified failure WL and / or an identified failure BL.
7. A method, include: The memory controller controls the circuit to read the codeword from the memory device; identifying, by defect map logic, a corresponding word line (WL) and a corresponding bit line (BL) for each bit in the codeword based at least in part on a memory device map; determining, by the defect map logic, whether any identified WL and / or any identified BL is faulty based at least in part on a defect map stored in a defect map circuit memory; configuring a decoding operation by an error correction circuit if any identified WL and / or any identified BL is determined to be faulty based on the defect map; if the codeword contains an error bit that is not a failed bit stored in the defect map circuit memory and associated with the identified WL and / or the identified BL, notifying the defect map logic by the error correction circuit; as well as The defect map logic determines whether the WL and / or BL associated with the corresponding WL bit error data and / or the corresponding BL bit error data is faulty based at least in part on the corresponding WL bit error data and / or the corresponding BL bit error data stored in the defect map circuit memory; and if the WL is faulty and / or the BL is faulty, the defect map logic updates the defect map stored in the defect map circuit memory and deletes the corresponding bit error data from the defect map circuit memory.
8. The method according to claim 7, in, Determining whether the WL and / or the BL is faulty includes determining a raw bit error rate (RBER) for the WL and / or the BL.
9. The method according to claim 7, in, The configuration is based at least in part on a selected error correction code.
10. The method according to claim 9, in, The error correction code includes a low-density parity check (LDPC) error correction code, a Reed-Solomon error correction code, or a Bose-Chaudhuri-Hocquenghem (BCH) error correction code.
11. The method according to claim 9, in, The selected error correction code is LDPC or Reed-Solomon, and the error correction circuit is used to erase each failed bit of the codeword, each failed bit being associated with an identified failed WL and / or an identified failed BL.
12. The method according to claim 9, in, The selected error correction code is BCH, and the error correction circuit attempts to decode the codeword using at least a portion of a plurality of possible values for one or more failure bits of the codeword, each failure bit being associated with an identified failure WL and / or an identified failure BL.
13. A system, include: Memory devices; as well as Memory controller, including: A memory controller control circuit configured to read a codeword from the memory device; defect map logic to identify a corresponding word line (WL) and a corresponding bit line (BL) for each bit in the codeword based at least in part on a memory device map, and to determine whether any identified WL and / or any identified BL is faulty based at least in part on the defect map; a defect map circuit memory configured to store the defect map and corresponding WL bit error data and / or corresponding BL bit error data; and error correction circuitry for configuring a decoding operation if any identified WL and / or any identified BL is determined to be faulty based on the defect map, wherein the error correction circuit is used to notify the defect map logic if the codeword contains an error bit, the error bit is not a fault bit stored in the defect map circuit memory and associated with the identified WL and / or the identified BL, And wherein the defect map logic is used to determine whether the WL and / or BL associated with the corresponding WL bit error data and / or the corresponding BL bit error data is faulty based at least in part on the corresponding WL bit error data and / or the corresponding BL bit error data; and if the WL is faulty and / or the BL is faulty, then in the defect map circuit memory, the defect map is updated and the corresponding bit error data is deleted.
14. The system of claim 13, in, Determining whether the WL and / or the BL is faulty includes determining a raw bit error rate (RBER) for the WL and / or the BL.
15. The system of claim 13, in, The decoding operation is configured based at least in part on the selected error correction code.
16. The system of claim 15, in, The error correction code includes a low-density parity check (LDPC) error correction code, a Reed-Solomon error correction code, or a Bose-Chaudhuri-Hocquenghem (BCH) error correction code.
17. The system of claim 15, in, The selected error correction code is LDPC or Reed-Solomon, and the error correction circuit is used to erase each failed bit of the codeword, each failed bit being associated with an identified failed WL and / or an identified failed BL.
18. The system of claim 15, in, The selected error correction code is BCH, and the error correction circuit is used to attempt to decode the codeword using at least a portion of a plurality of possible values of one or more failure bits of the codeword, each failure bit being associated with an identified failure WL and / or an identified failure BL.
19. A computer readable storage device having stored thereon instructions, which when executed by one or more processors, result in the following operations, the operations include: A method according to any one of claims 7 to 12.
20. A computer program product having a computer program stored thereon, which, when executed by one or more processors, results in the following operations: include: A method according to any one of claims 7 to 12.
Citation Information
Patent Citations
Methods and systems for staggered memory operations
CN106537365A
Controller device and operation method for non-volatile memory with 3-dimensional architecture
CN106935271A
Memory device and memory system
JP2008217916A
Decoder device and method for decoding data stored in storage medium
US20080301524A1
Erasure correction using single error detection parity
US20130227374A1
