Abstract: Provided are a computer program product, system, and method for receiving, at a secondary storage controller, information on modified data from a primary storage controller to use to calculate parity data. The secondary storage controller receives from the primary storage controller difference data calculated from modified data and a pre-modified version of the modified data for a primary group of tracks at the primary storage and one of the modified data and new primary parity data calculated at the primary storage controller from the modified data and the difference data. The secondary storage controller uses the difference data and one of the modified data and the new primary parity data to write new secondary parity data and the modified data to a secondary group of tracks at the secondary storage.

Abstract: Hardware accelerator memory address translation fault resolution is provided. A hardware accelerator and a switchboard are in communication with a processing core. The hardware accelerator determines at least one memory address translation related to an operation having a fault. The operation and the fault memory address translation are flushed from the hardware accelerator including augmenting the operation with an entity identifier. The switchboard forwards the operation with the fault memory address translation and the entity identifier from the hardware accelerator to a second buffer. The operating system repairs the fault memory address translation. The operating system sends the operation to the processing core utilizing an effective address based on the entity identifier. The switchboard, supported by the processing core, forwards the operation with the repaired memory address translation to a first buffer and the hardware accelerator executes the operation with the repaired address.

Abstract: A semiconductor device may include a memory bank and a plurality of mode registers that communicatively couple to each of the plurality of memory banks. The plurality of mode registers may include a pattern of data stored therein. The semiconductor device may also include a bank control that receives a write pattern command that causes the bank control to write the pattern of data into the memory bank, send a signal to a multiplexer to couple the plurality of mode registers to the memory bank, and write the pattern of data to the memory bank via the plurality of mode registers.

Abstract: The invention relates to a soft input decoding method and a decoder for generalized concatenated (GC) codes. The GC codes are constructed from inner nested block codes, such as binary Bose-Chaudhuri-Hocquenghem, BCH, codes and outer codes, such as Reed-Solomon, RS, codes. In order to enable soft input decoding for the inner block codes, a sequential stack decoding algorithm is used. Ordinary stack decoding of binary block codes requires the complete trellis of the code. In one aspect, the present invention applies instead a representation of the block codes based on the trellises of supercodes in order to reduce the memory requirements for the representation of the inner codes. This enables an efficient hardware implementation. In another aspect, the present invention provides a soft input decoding method and device employing a sequential stack decoding algorithm in combination with list-of-two decoding which is particularly well suited for applications that require very low residual error rates.

Abstract: An encoder of a flash memory controller is provided, which includes a barrel shifter module, an inverse matrix calculating circuit and a calculating circuit. The barrel shifter module processes multiple data blocks to generate multiple partial parity blocks including a first portion, a second portion and a third portion. The inverse matrix calculating circuit performs inverse matrix calculating operations on the first portion to generate a first portion of parity blocks. The calculating circuit performs inverse matrix calculating operations on the second portion and the third portion according to the first portion of the parity blocks, to generate a second portion of the parity blocks and a third portion of the parity blocks. The first portion of the parity blocks, the second portion of the parity blocks, and the third portion of the parity blocks serve as multiple parity blocks generated in response to encoding the data blocks.

Abstract: A solid state storage device using a prediction function is provided. The solid state storage device includes a control circuit and a non-volatile memory. The control circuit generates collection read operation commands. The collection read operation commands are temporarily stored in a command queue, and transmitted to the non-volatile memory. According to each of the collection read operation commands, the non-volatile memory generates a corresponding encoded read data to the control circuit. After the error correction circuit performs a decoding operation on the encoded read data, a decoded content is generated and a first count of the decoded content is transmitted to a first register of the register set. After the encoded read data is decoded, a value stored in the first register is a first parameter and the first parameter is inputted into a prediction function of the function storage circuit.

Abstract: A wireless device generates a High Efficiency Signal B (HE-SIG-B) field by Block Convolution Code (BCC) encoding and rate-matching a BCC block of the HE-SIG-B field, generates a Physical Layer Protocol Data Unit (PPDU) including the HE-SIG-B field, and transmits the PPDU. A total number N is a total number of bits of the HE-SIG-B field that precede the BCC block, and is greater than 0. The BCC block has a puncturing pattern depending on the total number N. A wireless device receives a PPDU. The PPDU includes an HE-SIG-B field that includes an encoded BCC block. The wireless device de-rate-matches the encoded BCC block having a puncturing pattern depending on a total number N. The total number N is a total number of decoded bits of the HE-SIG-B field that preceded the BCC block, and the total number N is greater than 0.

Abstract: A write method and a write apparatus for a storage device, where the write method includes: acquiring n numerical values that need to be written; determining n bits corresponding to the n numerical values, and information about a stuck-at fault included in the n bits; grouping the n bits into B groups of bits, so that the B groups of bits meet a grouping condition; and correspondingly writing the n numerical values according to information about a stuck-at fault included in each group of bits in the B groups of bits and a numerical value that needs to be written and that is corresponding to the information about the stuck-at fault included in each group of bits in the B groups of bits.

Abstract: Field error correction coding is particularly suitable for applications in non-volatile flash memories. We describe a method for error correction encoding of data to be stored in a memory device, a corresponding method for decoding a codeword matrix resulting from the encoding method, a coding device, and a computer program for performing the methods on the coding device, using a new construction for high-rate generalized concatenated (GC) codes. The codes, which are well suited for error correction in flash memories for high reliability data storage, are constructed from inner nested binary Bose-Chaudhuri-Hocquenghem (BCH) codes and outer codes, preferably Reed-Solomon (RS) codes. For the inner codes extended BCH codes are used, where only single parity-check codes are applied in the first level of the GC code. This enables high-rate codes.

Abstract: Techniques are described for performing conditional forward error correction (FEC) of network data. The techniques and solutions can be applied to suppress the transmission of redundant forward error correction information for data (e.g., frames of audio and/or video data) that can be effectively recovered at the receiving device (e.g., at the decoder). For example, a first computing device that is encoding and transmitting data (e.g., encoded audio data) to a second computing device can determine whether portions of data can be predicted (e.g., to a certain quality measure) at the second computing device. If the portions of data can be predicted, then the first computing device can skip sending redundant copies of the portions of data (e.g., can skip sending forward error correction information) in current network packets.

Abstract: A memory device includes a semiconductor memory unit, a controller circuit configured to communicate with a host through a serial interface, store write data to be written into a page of the semiconductor memory unit in a data buffer, and an error-correcting code (ECC) circuit configured to generate an error correction code from the write data if the ECC circuit is enabled. The controller circuit writes the error correction code with the write data into the page if the ECC circuit is enabled. A maximum column address of the page which is accessible from the host changes depending on whether or not the ECC circuit is enabled.

Abstract: “Shoot-through” timing failures in a scan chain of a defective semiconductor integrated circuit corrupt test pattern data used to perform failure analysis. Methods and procedures are provided to detect “shoot-through” conditions, determine the number of shoot-through scan cells, and to determine the location of the shoot-through cells within a scan chain. Reset test pattern results can be analyzed to identify candidate locations of shoot-through cells and when combined with candidate cell locations from analysis of physical clock distribution trees and potential clock-skew issues, the exact location of all shoot-through cells can be determined. Methods are also provided to use shoot-through cell locations to identify the defective clock net containing the physical defect causing the clock skew conditions needed to produce shoot-through timing failures.

Abstract: A terminal apparatus (1) is provided with a coding unit (7), a decoding unit (2), and a control unit (5) for controlling the coding unit and the decoding unit individually. Under control of the control unit, the coding unit codes a payload, a first number of error corrections (3), and identification information (6) that are to be transmitted, on the basis of a method indicated by the already-transmitted identification information to thereby generate first coded data. The decoding unit decodes newly-received second coded data on the basis of a method indicated by the identification information included in a decoding result of the already-received second coded data.

Abstract: An error-handling processing circuit and system are provided. The system can receive an error signal, such as an interrupt, and decouple (e.g., by a gate signal) a functional clock from a processing block, in some instances effectively halting the processing block's operation. This can prevent a cascade of interdependent errors, thereby avoiding producing redundant or confusing error information. The system can include the processing block, a debug clock not coupled to the processing block, and a data block (e.g., a register file) coupled to the debug clock and to an external input/output interface. The data block can be configured to continue receiving a clock signal via a multiplexer from the debug clock without disruption after the functional clock is decoupled, enabling the data block to remain operational for debugging.

Abstract: Configuration values for Lookup tables (LUTs) and programmable routing switches in an FPGA are provided by means of a number of flip flops arranges in a shift register. This shift register may receive test values in a factory test mode, and operational configuration values (implementing whatever functionality the client requires of the FPGA) in an operational mode. The bitstreams are provided at one end of the shift register, and clocked through until the last flip flop receives its value. Values may also be clocked out at the other end of the shift register to be compared to the initial bitstream in order to identify corruption of stored values e.g. due to radiation exposure. A clock gating architecture is proposed for loading data to or reading data from specific selected shift registers.

Abstract: This disclosure relates to testing of integrated artificial intelligence (AI) circuit with embedded memory to improve effective chip yield and to mapping addressable memory segments of the embedded memory to multilayer AI networks at the network level, layer level, parameter level, and bit level based on bit error rate (BER) of the addressable memory segments. The disclosed methods and systems allows for deployment of one or more multilayer AI networks in an AI circuit with sufficient model accuracy even when the embedded memory has an overall BER higher than a preferred overall threshold.

Abstract: A technique includes determining that a given memory device of a plurality of memory devices has failed and in response to the determination that the given memory device has failed, re-encoding a data unit associated with the given memory device. The data unit is associated with a payload and a symbol-based error correction code. The re-encoding includes determining a bit-based error correction code for the payload and replacing the data unit in the memory with the payload and the bit-based error correction code.

Abstract: A system for reducing analog noise in a noisy channel, comprising: an interface configured to receive analog channel output comprising a stream of noisy binary codewords of a linear code; and a computation component configured to perform the following: for each analog segment of the analog channel output of block length: calculating an absolute value representation and a sign representation of a respective analog segment, calculating a multiplication of a binary representation of the sign representation with a parity matrix of the linear code, inputting the absolute value representation and the outcome of the multiplication into a neural network for acquiring a neural network output, and estimating a binary codeword by component-wise multiplication of the neural network output and the sign representation.

Abstract: A first group of data blocks of a memory sub-system is determined. The first group of data blocks is associated with a failure condition. Also, a second group of data blocks of the memory sub-system is determined. The second group of data blocks is not associated with the failure condition. User data is received and system data of the memory sub-system that is associated with the user data is generated. The system data is stored at the first group of data blocks that is associated with the failure condition by using a first programming operation. The user data is stored at the second group of data blocks that is not associated with the failure condition by using a second programming operation. The second programming operation is different from the first programming operation.

Abstract: An integrated circuit (IC) includes an encoder circuit configured to receive input data including a plurality of data bits. A plurality of parity computation equations for a single error correct double error detect adjacent double error correct adjacent triple error detect (SECDEDADECADTED) Hamming code is received. A plurality of parity bits are computed using the plurality of parity computation equations. Write data including the data bits and the parity bits are provided to a write circuit. The write circuit writes the write data to a memory.