Memory system, method for controlling the same, and apparatus for decoding codeworks

By decoding and parallel decoding of polarized codewords using BCH subcodes, the problem of low polarization decoding throughput is solved, and efficient data correction and processing is achieved.

CN118942521APending Publication Date: 2024-11-12SAMSUNG ELECTRONICS CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202410582384.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-05-11
Filing Date
2024-05-11
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The resource-intensive operation of the polarization decoding scheme during the decoding phase results in a reduced throughput, and a simplified decoding process is required to improve the efficiency of the decoding scheme.

Method used

The polarized codewords are decoded by using the Bosch-Johhry-Hokwenheim (BCH) subcode, and the total throughput is improved through parallel decoding and intelligent pursuit decoding strategies of multiple frames.

Benefits of technology

Significantly improves the total throughput of the decoder, reduces resource consumption, and improves data processing efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942521A_ABST
    Figure CN118942521A_ABST
Patent Text Reader

Abstract

The invention discloses a storage system, a control method thereof, and an apparatus for decoding a codeword. A system, apparatus, and method for decoding information bits obtained from a storage device includes obtaining a frame corresponding to a codeword from the storage device; performing a first decoding operation on the frame, selecting at least one potential error bit based on the first decoding operation indicating that a number of errors is greater than a predetermined number, and performing a second decoding operation based on the at least one potential error bit; determining that the frame cannot be corrected by the first decoding operation and the second decoding operation based on the second decoding operation indicating that the number of errors is not equal to the predetermined number plus one, and determining that the frame cannot be corrected by the first decoding operation and the second decoding operation based on the second decoding operation indicating that the number of errors is equal to the predetermined number plus one, the frame is corrected based on a result of the second decoding operation to obtain a corrected frame, and an information bit corresponding to the codeword is obtained based on the corrected frame.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] This application is based upon and claims the benefit of priority of U.S. patent application No. 18 / 196,244 filed in the United States Patent and Trademark Office on May 11, 2023, the disclosure of which is incorporated herein by reference. Technical Field

[0002] Apparatus and methods consistent with embodiments relate to a process for performing error correction coding, and more particularly, to a process for decoding polar codewords using a Bose-Chaudhuri-Hocquenghem (BCH) subcode. Background Art

[0003] Data storage components may use error correction codes (ECC) to correct data corruption that may occur in the memory. There are some types of ECC encoding (eg, ECC encoding using Polar or SPolar Generalized Concatenated Code (GCC) encoding schemes).

[0004] However, polar decoding schemes may involve resource-intensive operations that may reduce throughput in the decoding stage. Therefore, there is a need for a decoding scheme that simplifies the decoding process to increase throughput. Summary of the invention

[0005] Systems, apparatus, and methods are provided for managing storage by decoding polar codewords using Bose-Chaudhuri-Hokwenheim (BCH) subcodes.

[0006] Additional aspects will be set forth in part in the description which follows and, in part, will be apparent from the description, or may be learned by practice of the presented embodiments.

[0007] According to one aspect of the disclosure, a storage system includes: a storage device configured to store multiple codewords; and at least one processor configured to: obtain a frame corresponding to the codeword from the storage device, perform a first decoding operation on the frame, select at least one potential error bit based on the first decoding operation indicating that the number of errors is greater than a predetermined number, and perform a second decoding operation based on the at least one potential error bit, determine that the frame cannot be corrected by the first decoding operation and the second decoding operation based on the second decoding operation indicating that the number of errors is equal to the predetermined number plus one, and correct the frame based on the result of the second decoding operation to obtain a corrected frame, and obtain the information bit corresponding to the codeword based on the corrected frame.

[0008] According to one aspect of the disclosure, a device for decoding a codeword including multiple frames includes: at least one processor, configured to: obtain a frame corresponding to the codeword from a storage device; perform a first Bose-Chaudhuri-Hokwenheim (BCH) decoding on the frame, select at least one potential error bit based on the first BCH decoding indicating that the number of errors is greater than a predetermined number, and perform a second BCH decoding based on the at least one potential error bit; determine that the frame cannot be corrected by the first BCH decoding and the second BCH decoding based on the second BCH decoding indicating that the number of errors is not equal to the predetermined number plus one; based on the second BCH decoding indicating that the number of errors is equal to the predetermined number plus one, correct the frame based on the result of the second BCH decoding to obtain a corrected frame, and obtain information bits corresponding to the codeword based on the corrected frame.

[0009] According to one aspect of the disclosure, a method for controlling a storage system is executed by at least one processor and includes: obtaining a codeword from a storage device, wherein the codeword includes multiple frames, and obtaining a frame from the multiple frames; performing a first decoding operation on the frame; based on the first decoding operation indicating that the number of errors is greater than a predetermined number, selecting at least one potential error bit, and performing a second decoding operation based on the at least one potential error bit; based on the second decoding operation indicating that the number of errors is not equal to the predetermined number plus one, determining that the frame cannot be corrected by the first decoding operation and the second decoding operation; based on the second decoding operation indicating that the number of errors is equal to the predetermined number plus one, correcting the frame based on the result of the second decoding operation to obtain a corrected frame; and obtaining information bits corresponding to the codeword based on the corrected frame.

[0010] According to one aspect of the disclosure, a method for decoding a codeword is performed by at least one processor and includes: obtaining a frame corresponding to the codeword from a storage device, performing a first Bose-Chaudhuri-Hokwenheim (BCH) decoding on the frame, selecting at least one potential error bit based on the first BCH decoding indicating that the number of errors is greater than a predetermined number, and performing a second BCH decoding based on the at least one potential error bit, determining that the frame cannot be corrected by the first BCH decoding and the second BCH decoding based on the second BCH decoding indicating that the number of errors is equal to the predetermined number plus one, and correcting the frame based on the result of the second BCH decoding to obtain a corrected frame, and obtaining information bits corresponding to the codeword based on the corrected frame. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other aspects, features and advantages of specific embodiments of the present disclosure will become more apparent from the following description in conjunction with the accompanying drawings, in which:

[0012] Figure 1 is a block diagram of a computer system according to an embodiment;

[0013] Figure 2A is a block diagram of a host storage system according to an embodiment;

[0014] Figure 2B is a block diagram of an ECC engine according to an embodiment;

[0015] Figure 2C is a block diagram of an ECC encoding circuit according to an embodiment;

[0016] Figure 2D is a block diagram of an ECC decoding circuit according to an embodiment;

[0017] Figure 2E is a block diagram of an AES engine according to an embodiment;

[0018] Figure 3 is a block diagram of a memory system according to an embodiment;

[0019] Figure 4 is a block diagram of a memory device according to an embodiment.

[0020] Figure 5 is a block diagram of a UFS system according to an embodiment.

[0021] Figure 6 is a block diagram of a decoder according to an embodiment.

[0022] Figure 7 is a block diagram illustrating a representation of a codeword frame according to an embodiment.

[0023] Fig. 8A is a block diagram of an initial decoder according to an embodiment.

[0024] Figure 8B is a block diagram of a syndrome calculation module according to an embodiment.

[0025] Figure 8C is a block diagram of a first initial decoder according to an embodiment.

[0026] Fig.8D is a block diagram of a second initial decoder according to an embodiment.

[0027] Fig. 9 is a flow chart of a process for performing error correction decoding on a frame according to an embodiment.

[0028] Fig.10 is a block diagram illustrating a process of decoding multiple frames in parallel according to an embodiment.

[0029] Fig.11is a flow chart of a process for controlling a storage system according to an embodiment.

[0030] Fig.12 is a block diagram of a data center according to an embodiment. DETAILED DESCRIPTION

[0031] Specifically, the ECC code may be selected such that the ECC encoding uses a Bose-Chaudhuri-Hocquenghem (BCH) code as a subcode of the polar code. Thus, according to an embodiment, a coded row, which may be referred to as a frame, may be or may include both polar codewords and BCH codewords, and thus may satisfy both polar and BCH requirements.

[0032] For example, t may represent the number of errors that can be corrected by a specific BCH code or a specific BCH decoder, and may be referred to as error correction capability. In an embodiment, a BCH code with t=2 may be a subcode of a polar code. Specifically, the first two syndromes (also referred to as syndromes) of the BCH code may be determined based on a polarization parity check (e.g., a polarization parity check bit included in a polarization codeword), and thus may be obtained by rearranging bits of the polarization codeword.

[0033] A BCH code with an error correction capability of t=2 may have 2 syndromes and may therefore correct up to two error bits. In an embodiment, the error correction capability of t=2 may not be sufficient to correct every error in a polar codeword. However, BCH decoding may be very efficient and therefore very fast compared to polar decoding. As a result, the overall throughput of the decoder may be improved by using BCH decoding, even if only some frames are successful.

[0034] Thus, embodiments may involve using a BCH decoder to decode at least some of the multiple polarization frames, which may significantly improve overall throughput even if the BCH decoder cannot decode every polarization frame.

[0035] Figure 1 is a diagram of a system 1000 in which an embodiment may be applied. Figure 1 The system 1000 may be, for example, a mobile system such as a portable communication terminal (e.g., a mobile phone), a smart phone, a tablet personal computer (PC), a wearable device, a healthcare device, or an Internet of Things (IoT) device. However, Figure 1 The system 1000 is not necessarily limited to a mobile system and may be a PC, a laptop computer, a server, a media player, or an automotive device (eg, a navigation device).

[0036] Reference Figure 1, the system 1000 may include a main processor 1100, a memory (e.g., 1200a and 1200b), and a storage device (e.g., 1300a and 1300b). In addition, the system 1000 may include at least one of an image capture device 1410, a user input device 1420, a sensor 1430, a communication device 1440, a display 1450, a speaker 1460, a power supply device 1470, and a connection interface 1480.

[0037] The main processor 1100 may control all operations of the system 1000, and more specifically, the main processor 1100 may control operations of other components included in the system 1000. The main processor 1100 may be implemented as a general-purpose processor, a dedicated processor, or an application processor.

[0038] The main processor 1100 may include at least one CPU core 1110, and also include a controller 1120 configured to control memories 1200a and 1200b and / or storage devices 1300a and 1300b. In some embodiments, the main processor 1100 may also include an accelerator 1130, which is a dedicated circuit for high-speed data operations (such as artificial intelligence (AI) data operations). The accelerator 1130 may include a graphics processing unit (GPU), a neural processing unit (NPU), and / or a data processing unit (DPU), and may be implemented as a chip physically separated from other components of the main processor 1100.

[0039] The memories 1200a and 1200b may be used as main memory devices of the system 1000. Although each of the memories 1200a and 1200b may include a volatile memory such as a static random access memory (SRAM) and / or a dynamic RAM (DRAM), each of the memories 1200a and 1200b may include a nonvolatile memory such as a flash memory, a phase change RAM (PRAM), and / or a resistive RAM (RRAM). The memories 1200a and 1200b may be implemented in the same package as the main processor 1100.

[0040] The storage devices 1300a and 1300b may be used as non-volatile storage devices configured to store data regardless of whether power is supplied thereto, and have a larger storage capacity than the memories 1200a and 1200b. The storage devices 1300a and 1300b may include storage controllers (STRG CTRL) 1310a and 1310b, respectively, and non-volatile memories (NVMs) 1320a and 1320b configured to store data via the control of the storage controllers 1310a and 1310b. Although the NVMs 1320a and 1320b may include flash memories having a two-dimensional (2D) structure or a three-dimensional (3D) V-NAND structure, the embodiment is not limited thereto, and the NVMs 1320a and 1320b may include other types of NVMs (such as PRAM and / or RRAM).

[0041] The storage devices 1300a and 1300b may be physically separated from the main processor 1100 and included in the system 1000 or implemented in the same package as the main processor 1100. In addition, the storage devices 1300a and 1300b may have various types of SSDs or memory cards and may be removably combined with other components of the system 1000 through an interface (such as the connection interface 1480 described below). The storage devices 1300a and 1300b may be devices that apply a standard protocol (such as Universal Flash Storage (UFS), Embedded Multimedia Card (eMMC), or Non-Volatile Memory Express (NVMe)), but are not limited thereto.

[0042] The image capture device 1410 may capture still images or moving images. The image capture device 1410 may include a camera, a camcorder, and / or a webcam.

[0043] The user input device 1420 may receive various types of data input by a user of the system 1000 and include a touch pad, a keypad, a keyboard, a mouse, and / or a microphone.

[0044] The sensor 1430 may detect various types of physical quantities that may be obtained from the outside of the system 1000 and convert the detected physical quantities into electrical signals. The sensor 1430 may include a temperature sensor, a pressure sensor, an illumination sensor, a position sensor, an acceleration sensor, a biosensor, and / or a gyro sensor.

[0045] The communication device 1440 may transmit and receive signals between other devices outside the system 1000 according to various communication protocols. The communication device 1440 may include an antenna, a transceiver, and / or a modem.

[0046] Display 1450 and speaker 1460 may be used as output devices configured to output visual information and auditory information, respectively, to a user of system 1000 .

[0047] The power supply device 1470 may appropriately convert power supplied from a battery embedded in the system 1000 and / or an external power source, and supply the converted power to each component of the system 1000 .

[0048] The connection interface 1480 may provide a connection between the system 1000 and an external device that is connected to the system 1000 and is capable of transmitting and receiving data to and from the system 1000. The connection interface 1480 may be implemented by using various interface schemes such as Advanced Technology Attachment (ATA), Serial ATA (SATA), External SATA (e-SATA), Small Computer Small Interface (SCSI), Serial Attached SCSI (SAS), Peripheral Component Interconnect (PCI), PCI Express (PCIe), NVMe, IEEE 1394, Universal Serial Bus (USB) interface, Secure Digital (SD) card interface, Multimedia Card (MMC) interface, eMMC interface, UFS interface, embedded UFS (eUFS) interface, and Compact Flash (CF) card interface.

[0049] Figure 2A is a block diagram of a host storage system 10 according to an example embodiment.

[0050] The host storage system 10 may include a host 100 and a storage device 200. In addition, the storage device 200 may include a storage controller 210 and an NVM 220. According to an example embodiment, the host 100 may include a host controller 110 and a host memory 120. The host memory 120 may be used as a buffer memory configured to temporarily store data to be transmitted to or received from the storage device 200.

[0051] The storage device 200 may include a storage medium configured to store data in response to a request from the host 100. As an example, the storage device 200 may include at least one of an SSD, an embedded memory, and a removable external memory. When the storage device 200 is an SSD, the storage device 200 may be a device that complies with the NVMe standard. When the storage device 200 is an embedded memory or an external memory, the storage device 200 may be a device that complies with the UFS standard or the eMMC standard. Each of the host 100 and the storage device 200 may generate a packet and send the packet according to the adopted standard protocol.

[0052] When the NVM 220 of the storage device 200 includes a flash memory, the flash memory may include a 2D NAND memory array or a 3D (or vertical) NAND (VNAND) memory array. As another example, the storage device 200 may include various other types of NVM. For example, the storage device 200 may include a magnetic RAM (MRAM), a spin transfer torque MRAM, a conductive bridge RAM (CBRAM), a ferroelectric RAM (FRAM), a PRAM, an RRAM, and various other types of memory.

[0053] According to an embodiment, the host controller 110 and the host memory 120 may be implemented as separate semiconductor chips. Alternatively, in some embodiments, the host controller 110 and the host memory 120 may be integrated in the same semiconductor chip. As an example, the host controller 110 may be any one of a plurality of modules included in an application processor (AP). The AP may be implemented as a system on chip (SoC). In addition, the host memory 120 may be an embedded memory included in the AP or an NVM or memory module located outside the AP.

[0054] The host controller 110 may manage an operation of storing data (eg, write data) of a buffer of the host memory 120 in the NVM 220 or an operation of storing data (eg, read data) of the NVM 220 in a buffer.

[0055] The storage controller (STRG CTRL) 210 may include a host interface 211, a memory interface 212, and a CPU 213. In addition, the storage controller 210 may further include a flash translation layer (FTL) 214, a package manager 215, a buffer memory 216, an error correction code (ECC) engine 217, and an advanced encryption standard (AES) engine 218. The storage controller 210 may also include a working memory in which the FTL 214 is loaded. The CPU 213 may execute the FTL 214 to control data write and read operations on the NVM 220.

[0056] The host interface 211 may transmit and receive packets to and from the host 100. The packet transmitted from the host 100 to the host interface 211 may include a command or data to be written to the NVM 220. The packet transmitted from the host interface 211 to the host 100 may include a response to a command or data read from the NVM 220. The memory interface 212 may transmit data to be written to the NVM 220 to the NVM 220 or receive data read from the NVM 220. The memory interface 212 may be configured to comply with a standard protocol such as Toggle or Open NAND Flash Interface (ONFI).

[0057] The FTL 214 may perform various functions such as an address mapping operation, a wear leveling operation, and a garbage collection operation. The address mapping operation may be an operation of converting a logical address received from the host 100 into a physical address for actually storing data in the NVM 220. The wear leveling operation may be a technique for preventing excessive degradation of a specific block by allowing the blocks of the NVM 220 to be used evenly. As an example, the wear leveling operation may be implemented using a firmware technique for balancing the erase counts of physical blocks. The garbage collection operation may be a technique for ensuring available capacity in the NVM 220 by erasing an existing block after copying valid data of the existing block to a new block.

[0058] The packet manager 215 may generate a packet according to a protocol agreed with an interface of the host 100, or parse various types of information from a packet received from the host 100. In addition, the buffer memory 216 may temporarily store data to be written to the NVM 220 or data to be read from the NVM 220. Although the buffer memory 216 may be a component included in the storage controller 210, the buffer memory 216 may be outside the storage controller 210.

[0059] The ECC engine 217 may perform error detection and correction operations on read data read from the NVM 220. More specifically, the ECC engine 217 may generate parity bits for write data to be written to the NVM 220, and the generated parity bits may be stored together with the write data in the NVM 220. During data reading from the NVM 220, the ECC engine 217 may correct errors in the read data by using the parity bits read from the NVM 220 together with the read data, and output the error-corrected read data.

[0060] The AES engine 218 may perform at least one of an encryption operation and a decryption operation on data input to the memory controller 210 by using a symmetric key algorithm.

[0061] Figure 2B yes Figure 2A Detailed diagram of the ECC engine 217. Figure 2B, the ECC engine 217 may include an ECC encoding circuit 510 and an ECC decoding circuit 520. In response to the ECC control signal ECC_CON, the ECC encoding circuit 510 may generate parity bits ECCP[0:7] for write data WData[0:63] to be written to memory cells of the memory cell array 221. The parity bits ECCP[0:7] may be stored in the ECC cell array 223. According to an embodiment, in response to the ECC control signal ECC_CON, the ECC encoding circuit 510 may generate parity bits ECCP[0:7] for write data WData[0:63] to be written to memory cells of the memory cell array 221 including defective cells.

[0062] In response to the ECC control signal ECC_CON, the ECC decoding circuit 520 may correct the error bit data by using the read data RData[0:63] read from the memory cells of the memory cell array 221 and the parity bits ECCP[0:7] read from the ECC cell array 223, and output the error-corrected data Data[0:63]. According to an embodiment, in response to the ECC control signal ECC_CON, the ECC decoding circuit 520 may correct the error bit data by using the read data RData[0:63] read from the memory cells of the memory cell array 221 including the defective cells and the parity bits ECCP[0:7] read from the ECC cell array 223, and output the error-corrected data Data[0:63].

[0063] Figure 2C yes Figure 2B Schematic diagram of an ECC encoding circuit 510.

[0064] Reference Figure 2C , the ECC encoding circuit 510 may include a parity generator 511, which receives the 64-bit write data WData[0:63] and the basic bit B[0:7] in response to the ECC control signal ECC_CON, and generates the parity bit ECCP[0:7] by using an XOR array operation. The basic bit B[0:7] may be a bit (e.g., a b'00000000 bit) used to generate the parity bit ECCP[0:7] of the 64-bit write data WData[0:63]. The basic bit B[0:7] may use other specific bits other than the b'00000000 bit.

[0065] Figure 2D yes Figure 2B Schematic diagram of an ECC decoding circuit 520.

[0066] Reference Figure 2D, the ECC decoding circuit 520 may include a syndrome generator 521, a coefficient calculator 522, a 1-bit error position detector 523, and an error corrector 524. The syndrome generator 521 may receive 64-bit read data and 8-bit parity bits ECCP[0:7] in response to the ECC control signal ECC_CON, and generate syndrome data S[0:7] by using an XOR array operation. The coefficient calculator 522 may calculate the coefficient of the error position equation by using the syndrome data S[0:7]. The error position equation may be an equation with the reciprocal of the error bit as a root. The 1-bit error position detector 523 may calculate the position of the 1-bit error by using the calculated error position equation (e.g., the coefficient of the calculated error position equation). The error corrector 524 may use the detection result of the 1-bit error position detector 523 (e.g., the position of the 1-bit error or the 1-bit error position information). The error corrector 524 can correct the error by inverting the logic value of the bit where the error occurs among the 64-bit read data RData[0:63] (i.e., the data sent to the global input / output line (GIO[0:63])) based on the determined 1-bit error location information, and output the error-corrected 64-bit data Data[0:63]. In an embodiment, the error location equation may correspond to the error locator polynomial (ELP) described herein.

[0067] Figure 2E yes Figure 2A Detailed diagram of the AES engine 218. The AES engine 218 can encrypt and decrypt data by using the AES algorithm, and includes an encryption module 218a and a decryption module 218b. Figure 2E The case where the encryption module 218a and the decryption module 218b are implemented as separate modules is shown, but in another case, one module capable of performing both encryption and decryption operations may be implemented in the AES engine 218. The buffer memory 216 may be a volatile memory used as a buffer or may be an NVM.

[0068] The AES engine 218 may receive the first data transmitted from the buffer memory 216. The encryption module 218a may encrypt the first data transmitted from the buffer memory 216 by using the encryption key and generate second data. The second data may be transmitted from the AES engine 218 to the buffer memory 216 and stored in the buffer memory 216.

[0069] In addition, the AES engine 218 may receive third data transmitted from the buffer memory 216. The third data may be data encrypted with the same encryption key as the encryption key used to encrypt the first data. The decryption module 218b may decrypt the third data transmitted from the buffer memory 216 using the same encryption key as the encryption key used to encrypt the first data, and generate fourth data. The fourth data may be transmitted from the AES engine 218 to the buffer memory 216 and stored in the buffer memory 216.

[0070] Figure 3 is a block diagram of a memory system 15 according to an embodiment. Figure 3 , the memory system 15 may include a memory device 17 and a memory controller 16. The memory system 15 may support a plurality of channels CH1 to CHm, and the memory device 17 may be connected to the memory controller 16 through the plurality of channels CH1 to CHm. For example, the memory system 15 may be implemented as a storage device such as an SSD.

[0071] The memory device 17 may include a plurality of NVM devices NVM11 to NVMmn. Each of the NVM devices NVM11 to NVMmn may be connected to one of the plurality of channels CH1 to CHm through a path corresponding thereto. For example, the NVM devices NVM11 to NVM1n may be connected to the first channel CH1 through paths W11 to W1n, and the NVM devices NVM21 to NVM2n may be connected to the second channel CH2 through paths W21 to W2n. In an example embodiment, each of the NVM devices NVM11 to NVMmn may be implemented as an arbitrary memory unit that may be operated according to a separate command from the memory controller 16. For example, each of the NVM devices NVM11 to NVMmn may be implemented as a chip or a die, but the disclosed embodiments are not limited thereto.

[0072] The memory controller 16 may transmit and receive signals to and from the memory device 17 through a plurality of channels CH1 to CHm. For example, the memory controller 16 may transmit and receive commands CMDa to CMDm, addresses ADDRa to ADDRm, and data DATAa to DATAm to and from the memory device 17 through the channels CH1 to CHm.

[0073] The memory controller 16 may select one of the NVM devices NVM11 to NVMmn connected to each of the channels CH1 to CHm by using a corresponding one of the channels CH1 to CHm, and transmit and receive signals to and from the selected NVM device. For example, the memory controller 16 may select the NVM device NVM11 from the NVM devices NVM11 to NVM1n connected to the first channel CH1. The memory controller 16 may transmit a command CMDa, an address ADDRa, and data DATAa to the selected NVM device NVM11 through the first channel CH1, or receive data DATAa from the selected NVM device NVM11.

[0074] The memory controller 16 may transmit and receive signals to and from the memory device 17 through different channels in parallel. For example, the memory controller 16 may transmit a command CMDb to the memory device 17 through the second channel CH2 while transmitting a command CMDa to the memory device 17 through the first channel CH1. For example, the memory controller 16 may receive data DATAb from the memory device 17 through the second channel CH2 while receiving data DATAa from the memory device 17 through the first channel CH1.

[0075] The memory controller 16 may control all operations of the memory device 17. The memory controller 16 may transmit signals to the channels CH1 to CHm and control each of the NVM devices NVM11 to NVMmn connected to the channels CH1 to CHm. For example, the memory controller 16 may transmit a command CMDa and an address ADDRa to the first channel CH1 and control one selected from the NVM devices NVM11 to NVM1n.

[0076] Each of the NVM devices NVM11 to NVMmn may operate via the control of the memory controller 16. For example, the NVM device NVM11 may program data DATAa based on a command CMDa, an address ADDRa, and data DATAa supplied to the first channel CH1. For example, the NVM device NVM21 may read data DATAb based on a command CMDb and an address ADDb supplied to the second channel CH2, and transmit the read data DATAb to the memory controller 16.

[0077] although Figure 3 An example is shown in which the memory device 17 communicates with the memory controller 16 through m channels and includes n NVM devices corresponding to each channel, but the number of channels and the number of NVM devices connected to one channel may be variously changed.

[0078] Figure 4is a block diagram of a memory device 300 according to an example embodiment. Figure 4 , the memory device 300 may include a control logic circuit system 320, a memory cell array 330, a page buffer 340, a voltage generator 350, and a row decoder 360. The memory device 300 may also include a memory interface circuit system 310. In addition, the memory device 300 may also include column logic, a pre-decoder, a temperature sensor, a command decoder, and / or an address decoder.

[0079] The control logic circuit system 320 may control all various operations of the memory device 300. The control logic circuit system 320 may output various control signals in response to the command CMD and / or the address ADDR from the memory interface circuit system 310. For example, the control logic circuit system 320 may output the voltage control signal CTRL_vol, the row address X-ADDR, and the column address Y-ADDR.

[0080] The memory cell array 330 may include a plurality of memory blocks BLK1 to BLKz (where z is a positive integer), each of which may include a plurality of memory cells. The memory cell array 330 may be connected to the page buffer 340 via the bit lines BL, and connected to the row decoder 360 via the word lines WL, the string selection lines SSL, and the ground selection lines GSL.

[0081] In an example embodiment, the memory cell array 330 may include a 3D memory cell array including a plurality of NAND strings. Each NAND string may include memory cells respectively connected to word lines stacked vertically on a substrate. U.S. Patent Nos. 7,679,133; 8,553,466; 8,654,587; 8,559,235; and U.S. Patent Publication No. 2011 / 0233648 are incorporated herein by reference. In an example embodiment, the memory cell array 330 may include a 2D memory cell array including a plurality of NAND strings arranged in row and column directions.

[0082] The page buffer 340 may include a plurality of page buffers PB1 to PBn (here, n is an integer greater than or equal to 3), and the plurality of page buffers PB1 to PBn may be connected to the memory cells respectively through a plurality of bit lines BL. The page buffer 340 may select at least one of the bit lines BL in response to the column address Y-ADDR. The page buffer 340 may operate as a write driver or a sense amplifier according to the operation mode. For example, during a programming operation, the page buffer 340 may apply a bit line voltage corresponding to the data to be programmed (e.g., data DATA from the memory interface circuit system 310) to the selected bit line. During a read operation, the page buffer 340 may sense the current or voltage of the selected bit line BL and sense the data stored in the memory cell.

[0083] The voltage generator 350 may generate various voltages for program, read, and erase operations based on the voltage control signal CTRL_vol. For example, the voltage generator 350 may generate a program voltage, a read voltage, a program verification voltage, and an erase voltage as the word line voltage VWL.

[0084] The row decoder 360 may select one of the plurality of word lines WL and one of the plurality of string selection lines SSL in response to the row address X-ADDR. For example, the row decoder 360 may apply a program voltage and a program verification voltage to the selected word line WL during a program operation, and apply a read voltage to the selected word line WL during a read operation.

[0085] Figure 5 2 is a diagram of a UFS system 2000 according to an embodiment. The UFS system 2000 may be a system conforming to the UFS standard promulgated by the Joint Electron Device Engineering Council (JEDEC), and includes a UFS host 2100, a UFS device 2200, and a UFS interface 2300. Figure 1 The description of system 1000 may also be used without the following Figure 5 The description of the conflict applies to the Figure 5 UFS system 2000.

[0086] Reference Figure 5 , the UFS host 2100 can be connected to the UFS device 2200 through the UFS interface 2300. Figure 1 When the main processor 1100 is an AP, the UFS host 2100 may be implemented as a part of the AP. The UFS host controller 2110 and the host memory 2140 may correspond to Figure 1 The UFS device 2200 may correspond to the controller 1120 of the main processor 1100 and the memories 1200a and 1200b. Figure 1 The storage devices 1300a and 1300b of the UFS device controller 2210 and the storage device (eg, NVM) 2220 may correspond to Figure 1 Storage controllers 1310a and 1310b and NVMs 1320a and 1320b.

[0087] The UFS host 2100 may include a UFS host controller 2110, an application 2120, a UFS driver 2130, a host memory 2140, and a UFS interconnect (UIC) layer 2150. The UFS device 2200 may include a UFS device controller 2210, an NVM 2220, a storage interface 2230, a device memory 2240, a UIC layer 2250, and a regulator 2260. The NVM 2220 may include a plurality of memory cells 2221. Although each memory cell 2221 may include a flash memory having a 2D structure or a 3D V-NAND structure, each memory cell 2221 may include another NVM (such as PRAM and / or RRAM). The UFS device controller 2210 may be connected to the NVM 2220 through a storage interface 2230. The storage interface 2230 may be configured to comply with a standard protocol (such as Toggle or ONFI).

[0088] The application 2120 may refer to a program that wants to communicate with the UFS device 2200 to use the functions of the UFS device 2200. The application 2120 may send an input-output request (IOR) to the UFS driver 2130 for an input / output (I / O) operation on the UFS device 2200. The IOR may refer to a data read request, a data storage (or write) request, and / or a data erase (or discard) request, but is not limited thereto.

[0089] The UFS driver 2130 may manage the UFS host controller 2110 through a UFS-Host Controller Interface (UFS-HCI). The UFS driver 2130 may convert the IOR generated by the application 2120 into a UFS command defined by the UFS standard, and send the UFS command to the UFS host controller 2110. One IOR may be converted into a plurality of UFS commands. Although the UFS command may be basically defined by the SCSI standard, the UFS command may be a command dedicated to the UFS standard.

[0090] The UFS host controller 2110 may transmit the UFS command converted by the UFS driver 2130 to the UIC layer 2250 of the UFS device 2200 through the UIC layer 2150 and the UFS interface 2300. During transmission of the UFS command, the UFS host register 2111 of the UFS host controller 2110 may function as a command queue (CQ).

[0091] The UIC layer 2150 on the UFS host 2100 side may include a Mobile Industry Processor Interface (MIPI) M-PHY 2151 and a MIPI UniPro 2152 , and the UIC layer 2250 on the UFS device 2200 side may further include a MIPI M-PHY 2251 and a MIPI UniPro 2252 .

[0092] The UFS interface 2300 may include a line configured to transmit a reference clock signal REF_CLK, a line configured to transmit a hardware reset signal RESET_n for the UFS device 2200 , a pair of lines configured to transmit a pair of differential input signals DIN_T and DIN_C, and a pair of lines configured to transmit a pair of differential output signals DOUT_T and DOUT_C.

[0093] The frequency of the reference clock signal REF_CLK provided from the UFS host 2100 to the UFS device 2200 may be one of 19.2 MHz, 26 MHz, 38.4 MHz, and 52 MHz, but is not limited thereto. The UFS host 2100 may change the frequency of the reference clock signal REF_CLK during operation (i.e., during a data transmission / reception operation between the UFS host 2100 and the UFS device 2200). The UFS device 2200 may generate clock signals having various frequencies according to the reference clock signal REF_CLK provided from the UFS host 2100 by using a phase-locked loop (PLL). In addition, the UFS host 2100 may set a data rate between the UFS host 2100 and the UFS device 2200 by using the frequency of the reference clock signal REF_CLK. That is, the data rate may be determined according to the frequency of the reference clock signal REF_CLK.

[0094] The UFS interface 2300 may support multiple lanes, each of which may be implemented as a pair of differential lines. For example, the UFS interface 2300 may include at least one receiving lane and at least one transmitting lane. Figure 5 In the embodiment, a pair of lines configured to transmit a pair of differential input signals DIN_T and DIN_C may constitute a receiving channel, and a pair of lines configured to transmit a pair of differential output signals DOUT_T and DOUT_C ​​may constitute a transmitting channel. Figure 5 One transmission channel and one reception channel are shown in FIG. 1 , but the number of transmission channels and the number of reception channels may be changed.

[0095] The receiving channel and the transmitting channel may transmit data based on a serial communication scheme. Full-duplex communication between the UFS host 2100 and the UFS device 2200 may be enabled due to a structure in which the receiving channel is separated from the transmitting channel. That is, while receiving data from the UFS host 2100 through the receiving channel, the UFS device 2200 may transmit the data to the UFS host 2100 through the transmitting channel. In addition, control data (e.g., commands) from the UFS host 2100 to the UFS device 2200 and user data to be stored in the NVM 2220 of the UFS device 2200 or read from the NVM 2220 of the UFS device 2200 by the UFS host 2100 may be transmitted through the same channel. Therefore, between the UFS host 2100 and the UFS device 2200, in addition to a pair of receiving channels and a pair of transmitting channels, there may be no need to further provide a separate channel for data transmission.

[0096] The UFS device controller 2210 of the UFS device 2200 may control all operations of the UFS device 2200. The UFS device controller 2210 may manage the NVM 2220 by using a logical unit (LU) 2211 (e.g., the 0th logical unit to the N-1th logical unit) as a logical data storage unit. The number of LUs 2211 may be 8, but is not limited thereto. The UFS device controller 2210 may include an FTL, and convert a logical data address (e.g., a logical block address (LBA)) received from the UFS host 2100 into a physical data address (e.g., a physical block address (PBA)) by using address mapping information of the FTL. A logical block configured to store user data in the UFS system 2000 may have a size within a predetermined range. For example, the minimum size of a logical block may be set to 4 kilobytes.

[0097] When a command from the UFS host 2100 is applied to the UFS device 2200 through the UIC layer 2250 , the UFS device controller 2210 may perform an operation in response to the command and transmit a completion response to the UFS host 2100 when the operation is completed.

[0098] As one example, when the UFS host 2100 intends to store user data in the UFS device 2200, the UFS host 2100 may send a data storage command to the UFS device 2200. When receiving a response ("Ready to Transfer" response) indicating that the UFS host 2100 is ready to receive user data (ready to transfer) from the UFS device 2200, the UFS host 2100 may send the user data to the UFS device 2200. The UFS device controller 2210 may temporarily store the received user data in the device memory 2240, and store the user data temporarily stored in the device memory 2240 at a selected location of the NVM 2220 based on the address mapping information of the FTL.

[0099] As another example, when the UFS host 2100 intends to read user data stored in the UFS device 2200, the UFS host 2100 may send a data read command to the UFS device 2200. The UFS device controller 2210, which has received the command, may read the user data from the NVM 2220 based on the data read command, and temporarily store the read user data in the device memory 2240. During the read operation, the UFS device controller 2210 may detect and correct errors in the read user data by using an ECC engine embedded therein. More specifically, the ECC engine may generate parity bits for write data to be written to the NVM 2220, and the generated parity bits may be stored in the NVM 2220 together with the write data. During the reading of data from the NVM 2220, the ECC engine may correct errors in the read data by using the parity bits read from the NVM 2220 together with the read data, and output the error-corrected read data.

[0100] In addition, the UFS device controller 2210 may transmit user data temporarily stored in the device memory 2240 to the UFS host 2100. In addition, the UFS device controller 2210 may further include an AES engine. The AES engine may perform at least one of an encryption operation and a decryption operation on data transmitted to the UFS device controller 2210 by using a symmetric key algorithm.

[0101] The UFS host 2100 may sequentially store commands to be sent to the UFS device 2200 in the UFS host register 2111 that may be used as a common queue, and sequentially send the commands to the UFS device 2200. In this case, the UFS host 2100 may send the next command waiting in the CQ to the UFS device 2200 even when the previously sent command is still being processed by the UFS device 2200 (i.e., even before receiving a notification that the previously sent command has been processed by the UFS device 2200). Therefore, the UFS device 2200 may also receive the next command from the UFS host 2100 during the processing of the previously sent command. The maximum number of commands (or queue depth) that can be stored in the CQ may be, for example, 32. In addition, the CQ may be implemented as a circular queue in which the start and end of the command line stored in the queue are indicated by a head pointer and a tail pointer.

[0102] Each of the plurality of memory cells 2221 may include a memory cell array and a control circuit configured to control the operation of the memory cell array. The memory cell array may include a 2D memory cell array or a 3D memory cell array. The memory cell array may include a plurality of memory cells. Although each of the memory cells is a single-level cell (SLC) configured to store 1 bit of information, each of the memory cells may be a cell configured to store 2 or more bits of information (such as a multi-level cell (MLC), a three-level cell (TLC), and a four-level cell (QLC)). The 3D memory cell array may include a vertical NAND string in which at least one memory cell is vertically oriented and located on another memory cell.

[0103] Voltages VCC, VCCQ1, and VCCQ2 may be applied to the UFS device 2200 as power supply voltages. Voltage VCC may be a main power supply voltage for the UFS device 2200 and may be in the range of 2.4V to 3.6V. Voltage VCCQ1 may be a power supply voltage for mainly supplying a low voltage to the UFS device controller 2210 and may be in the range of 1.14V to 1.26V. Voltage VCCQ2 may be a power supply voltage for mainly supplying a voltage lower than voltage VCC and higher than voltage VCCQ1 to an I / O interface such as MIPI M-PHY2251 and may be in the range of 1.7V to 1.95V. The power supply voltage may be supplied to the respective components of the UFS device 2200 through the regulator 2260. The regulator 2260 may be implemented as a group of unit regulators respectively connected to different power supply voltages among the above-mentioned power supply voltages.

[0104] As described above, embodiments may involve efficient BCH decoding with low error correction capability, which can correct t and (t+1) errors in polar codewords. As described above, an error correction capability of t=2 can be used, however, embodiments are not limited thereto. In embodiments, a BCH decoder can be used instead of a polar decoder to decode at least some of the polar codewords among a plurality of polar codewords that can be stored, for example, in a storage device, thereby increasing the overall throughput. In some embodiments, one or more polarization parity checks can be used to check or verify polar frames, and to perform smart chase decoding, examples of which are discussed in more detail below.

[0105] Figure 6 600 may correspond to any of the above elements. In an embodiment, the decoder 600 may use an input controller 604 and an inbound (IB) memory arbiter 608 to obtain multiple input codewords from multiple input buffers 601. The input codewords may be encoded using a GCC code (e.g., a SPolar GCC code) and may be obtained from a storage device. In an embodiment, the Spolar GCC code may represent a GCC code using a polar code and an RS code as a constituent code. The decoder 600 may decode and correct the input codeword using ECC encoding to obtain an output codeword, and may use an output controller 607 and an outbound (OB) memory arbiter 609 to provide the output codeword to multiple output buffers 603.

[0106] like Figure 6 As shown in , the decoder 600 may include an SPolar decoder 612 that may perform decoding (such as ECC decoding of an SPolar GCC codeword). In one embodiment, the SPolar decoder 612 may include a continuous cancellation list decoder (SCLD) 613, an SPolar controller 614, and a Reed-Solomon (RS) decoder 615. The SPolar controller 614 may control the SPolar decoder 612 to use the continuous cancellation list decoder (SCLD) 613 to decode the outer code of the SPolar GCC codeword, and to use the Reed-Solomon (RS) decoder 615 to decode the inner code of the Spolar GCC codeword. In an embodiment, information used by the SCLD 613 during decoding may be stored in the polar SCLD buffer 602. In an embodiment, the outer code may be a polar code and may correspond to a row or frame of the SPolar GCC codeword.

[0107] The decoder 600 may perform hard decision (HD) decoding, which may be controlled using an HD controller 605, and soft decision (SD) decoding, which may be controlled by an SD controller 606. In an embodiment, the SCLD 613 may have a latency of O(NlogN), which may cause throughput challenges in HD decoding, where the expected noise may be low and the expected throughput may be relatively high relative to the input rate. Therefore, the decoder 600 may use the initial decoder 610 to perform a first period or first stage of HD decoding directly based on the input frame without activating the SPolar decoder 612. In an embodiment, the next stage in HD decoding may be SBCH decoding using a super BCH (SBCH) decoder 611 and SPolar decoding using an SPolar decoder 612. In an embodiment, one or more of these stages may be pipelined.

[0108] As frames are received, the initial decoder 610 may perform initial decoding of the frames in order to speed up HD decoding throughput by reducing the number of failed frames at the next stage. For example, when the decoder 600 operates in HD mode, the initial decoder 610 may be activated by the HD controller 605 and may be capable of decoding at least some (e.g., approximately 50% of the input frames) of the input frames. Table 1 below shows the probability of various numbers of errors that a decoder operating in HD mode at a residual bit error rate (RBER) = 7e-3 may encounter in a 512-bit frame.

[0109] Table 1

[0110] Number of errors Probability 0 0.027 1 0.099 2 0.178 3 0.213 >3 1-0.518=0.482

[0111] As described above, the initial decoder 610 may receive a frame or codeword that meets the requirements of the BCH code and the polar code. However, in general, the polar frame may have 2 m bits, and a BCH frame can have 2 m -1 bits, where m is an integer. Therefore, the frame 700 that can be used as an input to the initial decoder 610 can be referred to as an extended BCH frame. In an embodiment, the BCH frame corresponding to the frame 700 may include information bits i and parity bits p*, and the polarization frame corresponding to the frame 700 may include all bits of the BCH frame and also include additional parity bits p'.

[0112] For example, Figure 7 As shown in , frame 700 may correspond to both a polar frame having 512 bits and a BCH frame having 511 bits, however, the embodiment is not limited thereto. Frame 700 may be received by at least one of decoder 600 and initial decoder 610 in a plurality of blocks, each of which may correspond to a clock cycle. For example, Figure 7 As shown in 1 、in 2 、……、in 15 The frame 700 is received, however the embodiments are not limited thereto.

[0113] In an embodiment, the additional parity bit p' may be a parity bit indicating the parity of all bits of the frame 700. Therefore, the initial decoder 610 may not use BCH decoding to decode the additional parity bit p', but may use the additional parity bit p' to perform checking or verification of the frame 700 after the frame 700 is decoded.

[0114] In an embodiment, the parity bits p* may be used to satisfy BCH code constraints (e.g., syndromes and incremental syndromes) and polar code constraints (e.g., static frozen bits and incremental frozen bits). Some parity bits are common to both BCH codes and polar codes, and some parity bits are unique. The parity bits of the polar code and BCH code for a specific phase may have different positions, and some frozen bits may be defined as "dynamic" according to the BCH constraints.

[0115] Frame 700 may have different representations depending on the operations performed by initial decoder 610. For example, when frame 700 is received by at least one of decoder 600 and initial decoder 610, frame 700 may be organized in BCH order, an example of which is shown as representation 701. Representation 701 may be used for BCH decoding operations (e.g., real-time syndrome calculation). Frame 700 may then be rearranged into an information side polarization representation, an example of which is shown as representation 702. Representation 702 may include information bit i and parity bit p=p*+p', and information bit i and parity bit p may be mixed throughout representation 702. Frame 700 may then be multiplied by a polar code generation matrix (also known as a polarization generator matrix) G to obtain a frozen side polarization representation, an example of which is shown as representation 703. Representation 703 may be used by SPolar decoder 612 and may include information bit i' and frozen bit f, and information bit i' and frozen bit f may be mixed throughout representation 703. In an embodiment, information bit i and information bit i' may not be the same, but may be related. If frame 700 is successfully decoded, frame 700 may be rearranged to represent 704 by separating frozen bit f from information bit i' before being output to the next stage, so as to facilitate effective RS decoding. In an embodiment, each BCH syndrome may be, for example, 9 bits, but the embodiment is not limited thereto. In an embodiment, some of the frozen bits f may be related to the BCH syndrome, and the rest may be used for verification operations (e.g., cyclic redundancy check (CRC)).

[0116] Table 2 below provides an example of the bit positions of the frozen bits and the dynamic frozen bits for a 512-bit frame, however embodiments are not limited thereto.

[0117] Table 2

[0118]

[0119] In the example frame corresponding to Table 2, the frozen bits that can be used for CRC checking can be 3, 5, 6, 9, 10, 17, 12, 18, 20, 7, 11, 13, 129, 130, 33, 34, 24, 36, 65, 66. In an embodiment, other bits can be common to BCH representation and polar representation without conditional coding. Therefore, these other bits can be called dynamic bits.

[0120] Fig. 8A is a block diagram of an initial decoder according to an embodiment. Fig. 8A As shown in , the initial decoder 610 may receive an input frame using, for example, a signal DATA_IN, and may receive a signal DIN_VALID indicating whether the input frame is valid and a signal HD_MODE indicating whether the decoder 600 is operating in an HD mode. The initial decoder 610 may include a syndrome calculation module 811, which may receive an input frame using, for example, the signal DATA_IN, and may generate a syndrome (e.g., syndrome S1 (or S2)). 1 ) and syndrome S3 (or S 3 )) and a signal SYND_DONE indicating that the syndrome calculation is completed. The initial decoder 610 may also include a first initial decoder 812, which may receive the syndrome and the signal SYND_DONE, and may generate an output frame CR_FRAME0 and a signal FR_CORRECT0, and the signal FR_CORRECT0 may indicate whether the output frame CR_FRAME0 is valid. In an embodiment, the output frame CR_FRAME0 may be arranged according to the representation 704. The initial decoder 610 may also include a second initial decoder 813, which may receive the syndrome and the signal FR_CORRECT0, and may generate an output frame CR_FRAME1, a signal FR_CORRECT1, and a signal FR_FAIL, and the signal FR_CORRECT1 may indicate whether the output frame CR_FRAME1 is valid, and the signal FR_FAIL may indicate whether the frame correction performed by the first initial decoder 812 and the second initial decoder 813 has failed.

[0121] like Fig. 8AAs shown in , the initial decoder 610 may also include an initial decoder controller 814, which may receive signals FR_CORRECT0, FR_CORRECT1, FR_FAIL, and DIN_VALID. The initial decoder controller 814 may include a frame index manager 815, which may assist in managing an error locator polynomial (ELP), which may be used in a later decoding stage and may be stored in an ELP module 816. The initial decoder controller 814 may control the operation of a RS syndrome (RSS) module 817, which may receive and store one or more of the output frames CR_FRAME0 and CR_FRAME1 based on a signal START generated by the initial decoder controller 814 and signals idx0 and idx1. The initial decoder controller 814 may control the operation of an input buffer (IB) write module 818, which may receive and store one or more coefficients of the ELP and information from the RSS module 817 based on a signal IBW_GO. In one embodiment, the initial decoder controller 814 may output a signal DECODE_DONE indicating whether decoding is completed and a signal DECODE_SUCCESS indicating whether decoding is successful.

[0122] In an embodiment, the initial decoder 610 may update the RS syndrome stored in the RSS module 817 and the ELP coefficients stored in the ELP module 816 to reflect the state of decoding (e.g., corrected frames and their frozen bits). When the last frame of the GCC codeword is decoded and the RS syndrome and ELP are updated, they may be written to the input buffer from the IB write module 818 (e.g., via the input buffer interface) for subsequent decoding stages. The RS syndrome and ELP may be used and maintained in subsequent decoding stages, for example, by the SBCH decoder 611 and the SPolar decoder 612 to perform GCC decoding.

[0123] In an embodiment, both RS syndrome and ELP updates may be completed in 16 cycles per frame to support throughput, and logic included in the initial decoder 610 may allow new updates in the pipeline or maintain a first-in-first-out (FIFO) buffer, which may be relatively small (e.g., a depth of 2) because the gap between updates may sometimes be less than 16 cycles. In an embodiment, RS syndrome updates may be performed using a dynamically incremented frozen value rather than directly utilizing a frozen bit.

[0124] Because the gap between successful frames is not constant, and a frame successfully decoded by the first initial decoder 812 may arrive before a previous frame that was decoded by the second initial decoder 813 and therefore took longer to decode, embodiments may support out-of-order syndromes and ELP updates. Fig.10 Discuss examples of this situation.

[0125] Figure 8B 8 is a block diagram of a syndrome calculation module according to an embodiment. The syndrome calculation module 811 may start syndrome calculation when a frame is input. In an embodiment, Figure 8B As shown in , the syndrome calculation module 811 can use Horner's law hardware with parallelism to calculate in real time according to the input width. For example, the hardware of the syndrome calculation module 811 can use 32 bits (for example, when Figure 8B When p in is 32), the operation is performed in parallel, but the embodiment is not limited thereto. Figure 8B As shown in i )(i=1, 3, ..., (2t-1), t is an integer greater than 0), the syndrome value can be α of the input polynomial i For example, to compute a syndrome with 32 bits of parallelism per cycle, there may be 32 input bits α 31 ...α 0 (in order from most significant bit to least significant bit) multiplied by the constant b 0 ……b 31 , and the feedback can be multiplied by α 32×i .

[0126] Figure 8C 812 is a block diagram of a first initial decoder according to an embodiment. The first initial decoder 812 may receive the syndrome calculated by the syndrome calculation module 811 and may perform BCH decoding with an error correction capability of t. Figure 8C As shown in FIG. 1 , the first initial decoder 812 may include a Berlekamp-Massey (BM) module 831, which may receive syndromes (e.g., syndromes S1 and S3) and may perform BM calculations to generate coefficients of the ELP polynomial (e.g., coefficients C1 (or C 1 ) and C2 (or C 2 )), and the signal BM_DONE indicating the completion of the BM algorithm.

[0127] In an embodiment, the first initial decoder 812 may perform BCH decoding with an error correction capability of t=2. Therefore, since only two iterations are processed, the BM calculation may be relatively simple and may be implemented by directly calculating all options for the first two iterations, taking into account that there may be zero, one, or two errors. In an embodiment, the difference Δ for the second iteration may be determined according to the following equation 1: 3 :

[0128] Δ 3 =S1 3 +S3 Equation 1

[0129] Therefore, based on the error correction capability of t=2, options for the output of the BM module 831 after two iterations are provided in Table 3 below:

[0130] Table 3

[0131]

[0132] like Figure 8C As further shown in , the first initial decoder 812 may include a Chien search (CS) module 832, which may receive coefficients obtained by the BM module 831 and may perform a CS calculation to determine up to t erroneous bits to be flipped in order to correct the input frame.

[0133] In an embodiment, based on the first initial decoder performing BCH decoding with an error correction capability of t=2, the CS calculation can be performed by iterative CS hardware, or by simpler calculations depending on the ELP order.

[0134] For example, for an ELP order of 1, the ELP may have a single solution provided by Equation 2 below:

[0135] 1+S 1 X=0 Equation 2

[0136] The root of equation 2 can be obtained as 1 / S 1 Therefore, the divider can be implemented in hardware (e.g., using a multiplexer). For an ELP order of 2, the ELP can be expressed according to the following equation 3:

[0137] ELP(x)=a 2 ·x 2 +a 1 ·x+1,a 1 ≠0, a 2 ≠0 Equation 3

[0138] Therefore, the ELP roots can be computed in several different ways (e.g., using parallel polynomial estimation, tables, or using matrix computations), examples of which are discussed below.

[0139] According to an embodiment, the roots of a polynomial of degree 2 with coefficients over a Galois field may be found using an m×m matrix A that may be precomputed for a Galois field. For example, for GF(2 m )(m=9), in the case of the primitive polynomial 1+x^4+x^9, the matrix A can be provided by the following equation 4:

[0140]

[0141] It can be GF(2 9The temporary variables b, c, d1, d of the elements in ) can be calculated according to the following equations 5 and 6:

[0142] c = 1 / a2, b = a1×c Equation 5

[0143] d1 = 1 / (a1 2 ), d = a2×d1 Equation 6

[0144] The vector y of m bits may be defined according to the following equation 7:

[0145] y = A × d Equation 7

[0146] If the most significant bit (MSB) of vector y (for example, y m-1 ) is not 0, this may indicate a failure. Otherwise, vector y may be left-shifted to vector y as shown in Equation 8 below new :

[0147] y new = (0, y 0 , y 1 , ..., y m-2 ) Equation 8

[0148] The root of the ELP can then be determined according to Equation 9 and Equation 10 below:

[0149] root1 = b × y Equation 9

[0150] root2 = root1 + b Equation 10

[0151] like Figure 8C As further shown in , the first initial decoder 812 may include a frame buffer 833 and a parity fixation module 834, the frame buffer 833 may provide the bits of the frame to be flipped, and the parity fixation module 834 may perform a parity check based on the additional parity bit p' after the error bit is flipped. The first initial decoder 812 may include a permutation module 835 and a polarization matrix multiplication module 836, the permutation module 835 may permute the frame into an information side polarization code arrangement (such as, representation 702), and the polarization matrix multiplication module 836 may multiply the frame by the polarization generator matrix G to obtain a frozen side polarization code arrangement (such as, representation 703), and the frozen side polarization code arrangement may be output as an output frame CR_FRAME0. The first initial decoder 812 may include a freeze check module 837, the freeze check module 837 may check the frozen bits of the frame to determine whether the frame is a valid polarization frame, and then output a signal FR_CORRECT0. For example, the freeze check module 837 may output a signal FR_CORRECT0 indicating that the output frame CR_FRAME0 is valid based on all the freeze bits being equal to zero.

[0152] Fig.8D 810 is a block diagram of a second initial decoder according to an embodiment. If the frame is not successfully corrected by the first initial decoder 812, the initial decoder 610 may activate the second initial decoder 813 to perform a smart chase decoding operation.

[0153] like Fig.8D As shown in , in an embodiment, the second initial decoder 813 may include a parity check module 841, which may perform a parity check based on the additional parity bit p' before the smart chase decoding operation is performed. For example, based on the parity check indicating that the number of errors is even, this may indicate that the only possibility of finding three errors in the frame is when the parity bit is also flipped. Therefore, it may be advantageous to declare the frame failed and skip the smart chase decoding operation to avoid potential miscorrection of the frame. If the parity check is 1, this may mean that the number of errors or flipped bits is odd, and the second initial decoder may continue to try to correct exactly three errors.

[0154] According to the smart chase decoding operation, the second initial decoder 813 may attempt to determine whether there are exactly t+1 errors in the frame. If so, the frame may be corrected without performing polar decoding. However, if the smart chase decoding operation indicates that there are any number of errors other than exactly t+1 errors, this may indicate that the frame is not correctable by the initial decoder 610. For example, if the smart chase decoding operation indicates that there are less than t+1 errors, this may indicate that the solution is invalid because less than t+1 errors should have been corrected by the first initial decoder 812 before reaching the second initial decoder 813. In addition, if there are more than t+1 errors, this may indicate that polar decoding is required to correctly correct all errors.

[0155] For example, in an embodiment, the second initial decoder 813 may attempt to correct exactly three errors by guessing the first erroneous bit ("chasing") and finding the other two errors using a BCH decoder with an error correction capability of exactly t=2, where t=2 may be represented as t==2.

[0156] like Fig.8D As shown in , the second initial decoder 813 may receive the syndrome calculated by the syndrome calculation module 811 and may perform a smart chase decoding operation to determine whether the input frame has exactly t+1 errors (eg, t+1=3). Fig.8D As shown in , the second initial decoder 813 may receive syndromes (eg, syndromes S1 and S3 ) and a signal FR_CORRECT0 .

[0157] like Fig.8DAs shown in , in order to perform the smart chase decoding operation, the second initial decoder 813 may include a bit selection module 842, and the bit selection module 842 may select the potential error bit. In an embodiment, the second initial decoder 813 may modify the frame by flipping the potential error bit to perform the smart chase decoding operation. The second initial decoder 813 may include one or more syndrome update modules 843 and one or more BCH modules 844, the syndrome update module 843 may update the syndrome based on the modified frame, and the BCH module 844 may perform BCH decoding on the modified frame based on the updated syndrome to try to find exactly t errors. The second initial decoder 813 may include a polarization check module 845, the polarization check module 845 may replace the frame successfully decoded by the one or more BCH modules 844 to generate an information side polarization frame, the information side polarization frame may be output as an output frame CR_FRAME1, and the frame may be multiplied by a polarization generator matrix G to generate a frozen side polarization frame. The polarization check module 845 may check the frozen bits of the frame and may output a signal FR_CORRECT1 indicating that the output frame CR_FRAME1 is valid based on all the frozen bits being equal to zero.

[0158] Typically, guessing the first error bit can be up to 2 m - Iterative process of 3 trials. However, if the bit selection module 842 is able to determine a smaller range that is guaranteed to have one error, the number of bits to be evaluated in a smart chase decoding operation can be greatly reduced.

[0159] For example, assuming there are 3 errors in a 512-bit frame, typically, guessing the first error bit may require up to 511-2 trials. However, considering the frozen bits included in the frozen side polarization frame represented by 703, each frozen bit can be connected to a list of bits in the input frame. Therefore, using the frozen bits as indicators, the chase range can be narrowed to only 128 bits. If the range indicator (e.g., one of the frozen bits) is set to 1 instead of 0, this may mean that an odd number of its connections are flipped. In an embodiment, this may mean that at least one or possibly up to three of the 128 connected bits are flipped. Therefore, the 128 bits of the set can be scanned, and it can be guaranteed that at least one of the flips is in the 128 bits.

[0160] For example, given a frame represented by x[0:511] in standard bit order, in an embodiment, the frozen bits of the polar frame may be represented as u[0], u[1], u[2], and u[3] as shown in Equation 11 below:

[0161]

[0162] By using these frozen bit parity checks, we can reduce the bit flip scan size to 128. For example, based on u[3]==1, the second initial decoder 813 can scan bits 384 to 511. Based on u[1]==1 and u[2]==0, the second initial decoder 813 can scan bits 256 to 383. Based on u[1]==0 and u[2]==1, the second initial decoder 813 can scan bits 128 to 255. Otherwise, the second initial decoder 813 can scan bits 0 to 127. However, embodiments are not limited to this. For example, if additional frozen bits are available, the scan range can be divided into more parts (e.g., eight parts or sixteen parts). In embodiments, scanning or chasing can be performed in any direction.

[0163] As described above, a new frame can be expected every 16 cycles. Therefore, in order to maintain throughput, the second initial decoder 813 can guess 8 bits in parallel per cycle. In an embodiment, based on finding more than one unique solution in the chase, a frame can be declared as a failure in order to avoid miscorrection of the frame.

[0164] In an embodiment, even though the number of bits to scan or chase in a smart chase decoding operation may be reduced as described above, there may still be a large number of bits to chase. However, even so, performing a reduced chase may still be much faster than having a polar decoder decode a frame.

[0165] In an embodiment, one or more syndrome update modules 843 may update the syndrome corresponding to the modified frame. For example, based on t=2, one or more syndrome update modules 843 may update the syndrome corresponding to the modified frame by correspondingly changing α i and α 3i Added to S1 and S3 to update the syndrome Si. In an embodiment, one or more syndrome update modules may be implemented using, for example, one or more of a table and an iterative constant multiplier.

[0166] In an embodiment, because the second initial decoder 813 can be used to find exactly t+1 errors, and because the first error is guessed as described above, the one or more BCH modules 844 can attempt to find exactly t errors. For example, the one or more BCH decoders can verify that the condition of exactly t=2 errors is valid, otherwise the BCH decoding can be considered to have failed. In an embodiment, the condition of exactly t=2 errors can be determined according to the following equation 12:

[0167] S1! = 0 && Δ 3 ! = 0 Equation 12

[0168] The corresponding ELP can be calculated according to the following equation 13:

[0169] ELP = 1 + (S1)X + (Δ 3 / S1)X 2 Equation 13

[0170] Fig. 9 6 is a flow chart of a process for performing error correction decoding on a frame according to an embodiment. In an embodiment, the initial decoder 610 may track live input frames, and thus the decoding throughput may be determined based on the input throughput. For example, in an embodiment, the input rate may be 32 bits per clock cycle, and thus the frame input may be completed in 512 / 32=16 cycles, so each hardware stage may need to be ready for the next frame after 16 cycles, however the embodiment is not limited thereto.

[0171] like Fig. 9 As shown in , at operation 901, processing may include calculating the syndrome of the input frame. The syndrome (e.g., syndrome S1 and S3) may be prepared in a cycle after the last input cycle corresponding to the frame, and a new calculation may be started immediately. In an embodiment, shortening and alignment may be performed according to the code layout. For example, the syndrome calculation module 811 may assume that the shortened bit is located at the most significant bit, and therefore may assume some leading zeros.

[0172] like Fig. 9 As shown in , at operation 902, the process 900 may include BCH decoding with t=2 and parity bit correction. Based on the syndrome being calculated (e.g., one cycle after the last input of the frame), the first initial decoder 812 may be activated and may perform BCH decoding with an error correction capability of t (e.g., t=2) to correct up to 2 error bits. Then, based on the BCH decoding success (e.g., based on determining that there are 0, 1, or 2 errors), the first initial decoder 812 may correct the frame. Then, the parity fixing module 834 may check the parity of the corrected frame based on the additional parity bit p', and may correct the additional parity bit p' if necessary, for example, by flipping the additional parity bit p'.

[0173] like Fig. 9 As shown in , at operation 903, process 900 may include: based on the decoding success at operation 902, performing polarization check on the frame using permutation module 835, polarization matrix multiplication module 836, and freeze check module 837. If the polarization check is successful, operation 903 may be considered successful. Otherwise, operation 903 may be considered a failure.

[0174] In an embodiment, operations 901, 902, and 903 may be performed by elements of the first initial decoder 812 as described above. In an embodiment, syndrome calculations may be performed in real time, and thus any additional cycles beyond the cycle required to obtain the input frame may not be required. Then, the BM module 831 and the CS module 832 may complete their operations within a few cycles (e.g., 3-5 cycles), and the parity fixation module 834, the permutation module 835, and the polarization matrix multiplication module 836 may complete their operations within, for example, 1-2 cycles.

[0175] like Fig. 9 As shown in , at operation 904, process 900 may include: determining that frame correction is successful based on the polarization check success at operation 903. For example, operation 904 may include: outputting the corrected frame as output frame CR_FRAME0, and setting signal FR_CORRECT0 to indicate that output frame CR_FRAME0 is valid.

[0176] like Fig. 9 As shown in , at operation 905 , process 900 may include: based on the BCH decoding failure at operation 902 or based on the polarization check failure at operation 903 , performing a parity check based on the additional parity bit p′ using the parity check module 841 .

[0177] Based on the parity check success at operation 905, process 900 may include activating other elements of the second initial decoder 813 and performing operations 906-909. In an embodiment, operations 906-909 may correspond to the smart chase decoding operations discussed above with respect to 8D.

[0178] like Fig. 9 As shown in , at operation 906, process 900 may include: based on the parity check success at operation 905, selecting a list of flip candidates based on the frozen bits. Fig.8D A list of flipping candidates is selected as discussed above.

[0179] like Fig. 9 As shown in , at operation 907 , process 900 may include selecting a potentially erroneous bit to be flipped from a list of flip candidates, and modifying the frame based on the selected potentially erroneous bit.

[0180] like Fig. 9 As shown in , at operation 908, process 900 may include performing BCH decoding on the modified frame using one or more BCH modules 844 to attempt to find exactly two errors.

[0181] In an embodiment, a plurality of potential error bits may be selected in operation 907, and operation 908 may include performing BCH decoding on a plurality of modified frames corresponding to the plurality of potential error bits in parallel. For example, operation 907 may include selecting eight potential error bits, and operation 908 may be performed on eight modified frames in parallel using eight BCH modules from one or more BCH modules 844.

[0182] like Fig. 9 As shown in FIG. 8 , at operation 909 , process 900 may include: based on the decoding success of the one or more frames at operation 908 , performing polarization check on the one or more frames using polarization check module 845 .

[0183] like Fig. 9 As shown in , at operation 904, process 900 may include determining that frame correction is successful based on the polarization check success at operation 909. For example, operation 904 may include outputting the corrected frame as output frame CR_FRAME1 and setting signal FR_CORRECT1 to indicate that output frame CR_FRAME1 is valid.

[0184] like Fig. 9 As shown in , at operation 910, process 900 may include determining that frame decoding failed based on the polarization check at operation 909 indicating multiple solutions or no solution. For example, operation 910 may include determining that the frame cannot be decoded by initial decoder 610.

[0185] Fig.10 is a block diagram illustrating a process of decoding multiple frames in a parallel pipeline architecture according to an embodiment. Fig.10 As shown in , a plurality of frames including frame k, frame k+1, frame k+2, and frame k+3 (each frame including 512 bits) can be decoded in parallel by an example of an initial decoder 610 using an error correction capability of t=2. Fig.10 As shown in , syndrome calculation is represented as “s”, BM calculation is represented as “B”, CS calculation is represented as “C”, and polarization check operation is represented as “G”.

[0186] exist Fig.10 In the example shown in , frame k has fewer than t+1=3 errors, frame k+1 has more than three errors, frame k+2 has exactly three errors, and frame k+3 has fewer than three errors.

[0187] Specifically, Fig.10As shown in , at ①, the first initial decoder 812 successfully decodes frame k. Then, frame k+1 is decoded by the BM module 831 and the CS module 832. However, at ②, frame k+1 fails the polarization check performed by the freeze check module 837, and at ③, the second initial decoder 813 is activated to start processing. At ④, the second initial decoder 813 completes scanning all 128 pursuit paths, and determines that there is no single solution, for example, because there are zero unique solutions or more than one unique solution. Therefore, the second initial decoder 813 determines at ④ that the initial decoder 610 cannot successfully decode frame k+1, and frame k+1 fails. At ⑤, while frame k+2 is still being decoded by the second initial decoder 813, the first initial decoder 812 successfully decodes frame k+3. Then, at ⑥, the second initial decoder 813 successfully decodes frame k+2. Therefore, as shown in Fig.10 As can be seen in FIG. 1 , according to an embodiment, frames may be corrected out of order due to the different number of cycles used by the first initial decoder 812 and the second initial decoder 813. As described above, in an embodiment, some stages in the decoder stream may take more than one cycle, however, latency may not be a problem as long as the hardware is ready for the next frame every 16 cycles.

[0188] Fig.11 is a flow chart of a process 11000 for controlling a storage device according to an embodiment. In some implementations, Fig.11 One or more processing blocks of the decoder 600, the initial decoder 610, the first initial decoder 812, the second initial decoder 813, or the above Figures 1 to 10 Any other elements described are performed.

[0189] like Fig.11 As shown in , at operation 1101, process 11000 may include obtaining a codeword from a storage device. In an embodiment, the codeword may correspond to the GCC codeword discussed above, and the plurality of frames included in the codeword may correspond to the frames 700 discussed above.

[0190] like Fig.11 As further shown in FIG. 1 , at operation 1102 , process 11000 may include obtaining a frame from among a plurality of frames.

[0191] like Fig.11 As further shown in FIG. 1 , at operation 1103, process 11000 may include performing a first decoding operation on the frame. In an embodiment, the first decoding operation may correspond to operation 902 performed by the first initial decoder 812 as described above.

[0192] like Fig.11As further shown in FIG. 1 , at operation 1104, process 11000 may include: selecting at least one potential error bit based on the first decoding operation indicating that the number of errors is greater than a predetermined number, and performing a second decoding operation based on the at least one potential error bit. In an embodiment, the first predetermined number may correspond to an error correction capability t. In an embodiment, the second decoding operation may correspond to a smart chase decoding operation performed by the second initial decoder 813 as described above.

[0193] like Fig.11 As further shown in FIG. 1 , at operation 1105 , process 11000 may include determining that the frame is not correctable by the first decoding operation and the second decoding operation based on the second decoding operation indicating that the number of errors is not equal to the predetermined number plus one. In an embodiment, the first predetermined number plus one may correspond to t+1.

[0194] like Fig.11 As further shown in, at operation 1106, process 11000 may include: based on the second decoding operation indicating that the number of errors is equal to the predetermined number plus one, correcting the frame based on the result of the second decoding operation to obtain a corrected frame.

[0195] like Fig.11 As further shown in , at operation 1107, process 11000 may include: in an embodiment, obtaining information bits corresponding to a codeword based on the corrected frame. In an embodiment, the information bits correspond to a decoded GCC codeword obtained by decoder 600 based on a frame decoded by initial decoder 610.

[0196] In an embodiment, based on the first decoding operation indicating that the number of errors is greater than a predetermined number, process 11000 may further include: selecting a plurality of potential error bits, and performing a plurality of second decoding operations based on the plurality of potential error bits.

[0197] In an embodiment, at least one of the first decoding operation and the second decoding operation may include a BCH decoding operation.

[0198] In an embodiment, the second decoding operation may include: modifying the frame by flipping a potential error bit from at least one selected potential error bit; and performing a BCH decoding operation on the modified frame, and processing 11000 may also include: determining that the number of errors is equal to the predetermined number plus one based on the BCH decoding operation indicating that the number of errors is equal to the predetermined number.

[0199] In an embodiment, based on the first decoding operation indicating that the number of errors is less than or equal to the predetermined number, the process 11000 may also include: correcting the frame based on the result of the first decoding operation to obtain a first potential corrected frame, performing a first check operation to determine whether the first potential corrected frame is valid, and based on the first check operation indicating that the first potential corrected frame is valid, determining a corrected frame based on the first potential corrected frame. In an embodiment, the first check operation may correspond to operation 903 performed by the elements of the first initial decoder 812 as described above.

[0200] In an embodiment, process 11000 may further include: performing a second decoding operation based on the first checking operation indicating that the first potentially corrected frame is invalid.

[0201] In an embodiment, based on the second decoding operation indicating that the number of errors is equal to the predetermined number plus one, the process 11000 may also include correcting the frame based on the result of the second decoding operation to obtain a second potential corrected frame, performing a second check operation to determine whether the second potential corrected frame is valid, and based on the second check operation indicating that the second potential corrected frame is valid, determining a corrected frame based on the second potential corrected frame. In an embodiment, the second check operation may correspond to operation 909 performed by the elements of the second initial decoder 813 as described above.

[0202] In an embodiment, the first check operation may include permuting the first potentially corrected frame to obtain a first polarized frame, multiplying the first polarized frame by a polarization generator matrix, and checking frozen bits corresponding to the first polarized frame, and the second check operation may include permuting the second potentially corrected frame to obtain a second polarized frame, multiplying the second polarized frame by a polarization generator matrix, and checking frozen bits corresponding to the second polarized frame.

[0203] although Fig.11 Example blocks of process 11000 are shown, but in some implementations, process 11000 may include Fig.11 The blocks depicted in the process 11000 may include additional blocks, fewer blocks, different blocks, or differently arranged blocks. Additionally or alternatively, two or more blocks in the blocks of the process 11000 may be arranged or combined in any order, or executed in parallel.

[0204] Fig.12 is a diagram of a data center 3000 to which a memory device is applied according to an embodiment.

[0205] Reference Fig.12, the data center 3000 may be a facility that collects various types of data and provides services, and is referred to as a data storage center. The data center 3000 may be a system for operating a search engine and a database, and may be a computing system used by a company (such as a bank) or a government agency. The data center 3000 may include application servers 3100 to 3100n and storage servers 3200 to 3200m. The number of application servers 3100 to 3100n and the number of storage servers 3200 to 3200m may be selected differently according to the embodiment. The number of application servers 3100 to 3100n may be different from the number of storage servers 3200 to 3200m.

[0206] The application server 3100 or the storage server 3200 may include at least one of the processors 3110 and 3210 and the memories 3120 and 3220. The storage server 3200 will now be described as an example. The processor 3210 may control all operations of the storage server 3200, access the memory 3220, and execute instructions and / or data loaded in the memory 3220. The memory 3220 may be a double data rate synchronous DRAM (DDR SDRAM), a high bandwidth memory (HBM), a hybrid memory cube (HMC), a dual in-line memory module (DIMM), an Optane DIMM, and / or a non-volatile DIMM (NVMDIMM). In some embodiments, the number of processors 3210 and the memory 3220 included in the storage server 3200 may be selected differently. In an embodiment, the processor 3210 and the memory 3220 may provide a processor-memory pair. In an embodiment, the number of processors 3210 may be different from the number of memories 3220. The processor 3210 may include a single-core processor or a multi-core processor. The above description of the storage server 3200 may be similarly applied to the application server 3100. In some embodiments, the application server 3100 may not include the storage device 3150. The storage server 3200 may include at least one storage device 3250. The number of storage devices 3250 included in the storage server 3200 may be variously selected according to embodiments.

[0207] The application servers 3100 to 3100n can communicate with the storage servers 3200 to 3200m through the network 3300. The network 3300 can be implemented by using Fibre Channel (FC) or Ethernet. In this case, FC can be a medium for relatively high-speed data transmission, and an optical switch with high performance and high availability is used. According to the access method of the network 3300, the storage servers 3200 to 3200m can be provided as file storage devices, block storage devices, or object storage devices.

[0208] In an embodiment, the network 3300 may be a storage-specific network such as a storage area network (SAN). For example, the SAN may be an FC-SAN using an FC network and implemented according to the FC protocol (FCP). As another example, the SAN may be an Internet Protocol (IP)-SAN, which uses a transmission control protocol (TCP) / IP network and is implemented according to a SCSI or Internet SCSI (iSCSI) protocol over TCP / IP. In another embodiment, the network 3300 may be a general network such as a TCP / IP network. For example, the network 3300 may be implemented according to protocols such as FC over Ethernet (FCoE), network attached storage (NAS), and NVMe over network (NVMe-oF).

[0209] Hereinafter, the application server 3100 and the storage server 3200 will be mainly described. The description of the application server 3100 may be applied to another application server 3100n, and the description of the storage server 3200 may be applied to another storage server 3200m.

[0210] The application server 3100 may store data requested to be stored by a user or client in one of the storage servers 3200 to 3200m through the network 3300. In addition, the application server 3100 may obtain data requested to be read by a user or client from one of the storage servers 3200 to 3200m through the network 3300. For example, the application server 3100 may be implemented as a network server or a database management system (DBMS).

[0211] The application server 3100 may access a memory 3120n or a storage device 3150n included in another application server 3100n through the network 3300. Alternatively, the application server 3100 may access a memory 3220 to 3220m or a storage device 3250 to 3250m included in the storage servers 3200 to 3200m through the network 3300. Therefore, the application server 3100 may perform various operations on the data stored in the application servers 3100 to 3100n and / or the storage servers 3200 to 3200m. For example, the application server 3100 may execute an instruction for moving or copying data between the application servers 3100 to 3100n and / or the storage servers 3200 to 3200m. In this case, data may be moved from storage devices 3250 to 3250m of storage servers 3200 to 3200m to storage 3120 to 3120n of application servers 3100 to 3100n directly or through storage 3220 to 3220m of storage servers 3200 to 3200m. Data moved through network 3300 may be data encrypted for security or privacy.

[0212] The storage server 3200 will now be described as an example. The interface (I / F) 3254 may provide a physical connection between the processor 3210 and the controller (CTRL) 3251 and a physical connection between the network interconnect (NIC) 3240 and the controller 3251. For example, the interface 3254 may be implemented using a direct attached storage (DAS) solution, in which the storage device 3250 is directly connected to a dedicated cable. For example, the interface 3254 may be implemented using various interface solutions (such as ATA, SATA, e-SATA, SCSI, SAS, PCI, PCIe, NVMe, IEEE 1394, USB interface, SD card interface, MMC interface, eMMC interface, UFS interface, eUFS interface, and / or CF card interface).

[0213] The storage server 3200 may further include a switch 3230 and a NIC (Network Interconnect) 3240. The switch 3230 may selectively connect the processor 3210 to the storage device 3250 or selectively connect the NIC 3240 to the storage device 3250 via the control of the processor 3210.

[0214] In an embodiment, the NIC 3240 may include a network interface card and a network adapter. The NIC 3240 may be connected to the network 3300 through a wired interface, a wireless interface, a Bluetooth interface, or an optical interface. The NIC 3240 may include an internal memory, a digital signal processor (DSP), and a host bus interface, and is connected to the processor 3210 and / or the switch 3230 through the host bus interface. The host bus interface may be implemented as one of the above examples of the interface 3254. In an embodiment, the NIC 3240 may be integrated with at least one of the processor 3210, the switch 3230, and the storage device 3250.

[0215] In the storage servers 3200 to 3200m (e.g., the first storage server to the Mth storage server) or the application servers 3100 to 3100n (e.g., the first application server to the Nth application server), the processor may send a command to the storage devices 3150 to 3150n and 3250 to 3250m or the memories 3120 to 3120n and 3220 to 3220m, and program or read the data. In this case, the data may be data whose errors are corrected by the ECC engine. The data may be data on which a data bus inversion (DBI) operation or a data masking (DM) operation is performed, and may include cyclic redundancy code information. The data may be data encrypted for security or privacy.

[0216] The storage devices 3150 to 3150n and 3250 to 3250m may send control signals and command / address signals to the NAND flash memory devices (or NAND) 3252 to 3252m in response to a read command received from the processor. Therefore, when data is read from the NAND flash memory devices 3252 to 3252m, a read enable (RE) signal may be input as a data output control signal, and thus, data may be output to the DQ bus. The data strobe signal DQS may be generated using the RE signal. The command and address signals may be latched in the page buffer according to the rising edge or falling edge of the write enable (WE) signal.

[0217] The controller 3251 may control all operations of the storage device 3250. In an embodiment, the controller 3251 may include an SRAM. The controller 3251 may write data to the NAND flash memory device 3252 in response to a write command, or read data from the NAND flash memory device 3252 in response to a read command. For example, a write command and / or a read command may be provided from the processor 3210 of the storage server 3200, the processor 3210m of another storage server 3200m, or the processors 3110 and 3110n of the application servers 3100 and 3100n. The DRAM 3253 may temporarily store (or buffer) data to be written to the NAND flash memory device 3252 or data read from the NAND flash memory device 3252. In addition, the DRAM 3253 may store metadata. Here, the metadata may be user data or data generated by the controller 3251 to manage the NAND flash memory device 3252. The storage device 3250 may include a secure element (SE) for security or privacy.

[0218] As is conventional in the field, embodiments are described and illustrated in the accompanying drawings according to functional blocks, units and / or modules. It will be appreciated by those skilled in the art that these blocks, units and / or modules are physically implemented by electronic (or optical) circuits (such as, logic circuits, discrete components, microprocessors, hard-wired circuits, memory elements, wiring connections, etc.), and electronic (or optical) circuits can be formed using semiconductor-based manufacturing techniques or other manufacturing techniques. In the case where blocks, units and / or modules are implemented by microprocessors or the like, they can be programmed using software (e.g., microcode) to perform the various functions discussed herein, and can be optionally driven by firmware and / or software. Optionally, each block, unit and / or module can be implemented by dedicated hardware, or implemented as a combination of dedicated hardware for performing some functions and a processor (e.g., one or more programmed microprocessors and associated circuit systems) for performing other functions. In addition, without departing from the scope of the present disclosure, each block, unit and / or module of the embodiment can be physically separated into two or more interactive and discrete blocks, units and / or modules. Furthermore, the blocks, units and / or modules of the embodiments may be physically combined into more complex blocks, units and / or modules without departing from the scope of the present disclosure.

[0219] The various operations of the above-described methods may be performed by any suitable means capable of performing the operations, such as various hardware and / or software components, circuits and / or modules.

[0220] The software may include an ordered listing of executable instructions for implementing logical functions and may be embodied in any "processor-readable medium" for use by or in conjunction with an instruction execution system, device or apparatus (such as a single-core or multi-core processor or a system containing a processor).

[0221] The blocks or steps of the methods or algorithms and functions described in conjunction with the embodiments disclosed herein may be implemented directly in hardware, software modules executed by a processor, or a combination of the two. If implemented in software, the functions may be stored as one or more instructions or codes on or transmitted through a tangible, non-transitory computer-readable medium. The software module may reside in a random access memory (RAM), flash memory, read-only memory (ROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), registers, a hard disk, a removable disk, a CD ROM, or any other form of storage medium known in the art.

[0222] The foregoing is illustrative of particular embodiments and should not be construed as limiting thereof. Although a few embodiments have been described, those skilled in the art will readily appreciate that many modifications may be made in the embodiments without materially departing from the scope of the present disclosure.

Claims

1. A storage system, include: A storage device configured to store a plurality of codewords; as well as At least one processor configured to: Obtaining a frame corresponding to the codeword from a storage device, performing a first decoding operation on the frame, selecting at least one potential error bit based on the first decoding operation indicating that the number of errors is greater than a predetermined number, and performing a second decoding operation based on the at least one potential error bit, determining that the frame cannot be corrected by the first decoding operation and the second decoding operation based on the second decoding operation indicating that the number of errors is not equal to the predetermined number plus one, and Based on the second decoding operation indicating that the number of errors is equal to the predetermined number plus one, correcting the frame based on a result of the second decoding operation to obtain a corrected frame, and Information bits corresponding to the codeword are obtained based on the corrected frame.

2. The storage system according to claim 1, in, The at least one processor is further configured to perform the following steps based on the first decoding operation indicating that the number of errors is greater than the predetermined number: Select multiple potential error bits, and A plurality of second decoding operations are performed based on the plurality of potentially erroneous bits.

3. The storage system according to claim 1, in, At least one of the first decoding operation and the second decoding operation comprises a Bose-Chaudhuri-Hokkewenheim (BCH) decoding operation.

4. The storage system according to claim 3, in, To perform the second decoding operation, the at least one processor is further configured to: modifying the frame by flipping a selected potentially erroneous bit among the at least one potentially erroneous bit; and performing a BCH decoding operation on the modified frame, and The at least one processor is further configured to: determine that the number of errors is equal to the predetermined number plus one based on the BCH decoding operation indicating that the number of errors is equal to the predetermined number.

5. The storage system according to any one of claims 1 to 4, in, The at least one processor is further configured to perform the following steps based on the first decoding operation indicating that the number of errors is less than or equal to the predetermined number: correcting the frame based on a result of the first decoding operation to obtain a first potentially corrected frame, performing a first check operation to determine whether the first potentially corrected frame is valid, and The corrected frame is determined based on the first potentially corrected frame based on the first potentially corrected frame, based on the first checking operation indicating that the first potentially corrected frame is valid.

6. The storage system according to claim 5, in, The at least one processor is further configured to perform a second decoding operation based on the first checking operation indicating that the first potentially corrected frame is invalid.

7. The storage system according to claim 6, in, The at least one processor is further configured to perform the following steps based on the second decoding operation indicating that the number of errors is equal to the predetermined number plus one: correcting the frame based on a result of the second decoding operation to obtain a second potentially corrected frame, performing a second check operation to determine whether the second potentially corrected frame is valid, and The corrected frame is determined based on the second potentially corrected frame based on the second potentially corrected frame, based on the second checking operation indicating that the second potentially corrected frame is valid.

8. The storage system according to claim 7, in, The first check operation includes: permuting the first potentially corrected frame to obtain a first polarized frame, multiplying the first polarized frame by a polarization generator matrix, and checking frozen bits corresponding to the first polarized frame, and The second checking operation includes: replacing the second potential correction frame to obtain a second polarization frame, multiplying the second polarization frame by a polarization generator matrix, and checking frozen bits corresponding to the second polarization frame.

9. A device for decoding a codeword comprising a plurality of frames, the device include: At least one processor configured to: Obtaining a frame corresponding to the codeword from a storage device, performing a first Bose-Chaudhuri-Hokkewenheim (BCH) decoding on the frame, selecting at least one potential error bit based on the first BCH decoding indicating that the number of errors is greater than a predetermined number, and performing a second BCH decoding based on the at least one potential error bit, determining that the frame cannot be corrected by the first BCH decoding and the second BCH decoding based on the second BCH decoding indicating that the number of errors is not equal to the predetermined number plus one, Based on the second BCH decoding indicating that the number of errors is equal to the predetermined number plus one, correcting the frame based on the result of the second BCH decoding to obtain a corrected frame, and Information bits corresponding to the codeword are obtained based on the corrected frame.

10. The device according to claim 9, in, The at least one processor is further configured to perform the following steps based on the number of first BCH decoding indication errors being greater than the predetermined number: Select multiple potential error bits, and A plurality of second decoding operations are performed based on the plurality of potentially erroneous bits.

11. The device according to claim 9, in, The at least one processor is further configured to perform the following steps based on the number of first BCH decoding indication errors being less than or equal to the predetermined number: Correcting the frame based on the result of the first BCH decoding to obtain a potentially corrected frame, permuting the potentially corrected frame to obtain a polar frame, Multiply the polarimetric frame by the polarimetric generator matrix, obtain the frozen bits based on the result of the multiplication, and The corrected frame is determined based on the potentially corrected frame based on the frozen bits being equal to zero.

12. The device according to claim 11, in, The at least one processor is further configured to perform a second BCH decoding over a reduced range based on the frozen bits not being equal to zero.

13. The device according to claim 9, in, The at least one processor is further configured to perform the following steps based on the number of second BCH decoding indication errors being equal to the predetermined number plus one: Correcting the frame based on the result of the second BCH decoding to obtain a potentially corrected frame, permuting the potentially corrected frame to obtain a polar frame, Multiply the polarimetric frame by the polarimetric generator matrix, obtain the frozen bits based on the result of the multiplication, and The corrected frame is determined based on the potentially corrected frame based on the frozen bits being equal to zero.

14. A method for controlling a storage system, the method being executed by at least one processor and include: Obtaining a codeword from a storage device, wherein the codeword includes a plurality of frames, obtaining a frame from among the plurality of frames; performing a first decoding operation on the frame; selecting at least one potentially erroneous bit based on the first decoding operation indicating that the number of errors is greater than a predetermined number, and performing a second decoding operation based on the at least one potentially erroneous bit; determining that the frame cannot be corrected by the first decoding operation and the second decoding operation based on the second decoding operation indicating that the number of errors is not equal to the predetermined number plus one; Based on the second decoding operation indicating that the number of errors is equal to the predetermined number plus one, correcting the frame based on a result of the second decoding operation to obtain a corrected frame; and Information bits corresponding to the codeword are obtained based on the corrected frame.

15. The method according to claim 14, further comprising: include: Based on the first decoding operation indicating that the number of errors is greater than the predetermined number, a plurality of potential error bits are selected, and a plurality of second decoding operations are performed based on the plurality of potential error bits.

16. The method according to claim 14, in, At least one of the first decoding operation and the second decoding operation comprises a Bose-Chaudhuri-Hokkewenheim (BCH) decoding operation.

17. The method according to claim 16, in, The second decoding operation includes: modifying the frame by flipping a selected potentially erroneous bit among the at least one potentially erroneous bit; and performing a BCH decoding operation on the modified frame, and The method further includes: determining that the number of errors is equal to the predetermined number plus one based on the BCH decoding operation indicating that the number of errors is equal to the predetermined number.

18. The method according to any one of claims 14 to 17, further comprising performing the following steps based on the first decoding operation indicating that the number of errors is less than or equal to the predetermined number: correcting the frame based on a result of the first decoding operation to obtain a first potentially corrected frame; performing a first check operation to determine whether the first potentially corrected frame is valid; and The corrected frame is determined based on the first potentially corrected frame based on the first potentially corrected frame, based on the first checking operation indicating that the first potentially corrected frame is valid.

19. The method according to claim 18, further comprising: include: Based on the first checking operation indicating that the first potentially corrected frame is invalid, a second decoding operation is performed.

20. The method according to claim 19, further comprising performing the following steps based on the second decoding operation indicating that the number of errors is equal to the predetermined number plus one: correcting the frame based on a result of the second decoding operation to obtain a second potentially corrected frame; performing a second check operation to determine whether the second potentially corrected frame is valid; as well as The corrected frame is determined based on the second potentially corrected frame based on the second potentially corrected frame, based on the second checking operation indicating that the second potentially corrected frame is valid.

Citation Information

Patent Citations

  • Three-Dimensional Semiconductor Memory Devices And Methods Of Fabricating The Same

    US20110233648A1

  • High throughput polar codeword decoding by decoding BCH sub-code in polar code structure

    US20240380417A1

  • Vertical-type non-volatile memory devices

    US7679133B2