Agere Systems Inc.

Avago Technologies General IP (singapore) Pte. Ltd.

Lsi Corporation

Other

Applied Micro Circuits Corporation

Avago Technologies General IP Pte, Ltd.

Nils Graef

Erich Franz Haratsch

Joachim S Hammerschmidt

Zachary A Keirn

Shaohua Yang

Kiran Kumar Gunnam

Johnson Yen

Hao Zhong

Yang Han

Yuan Xing Lee

Andrei Vityaev

Dariush Dabiri

Changyou Xu

Victor A Krachkovsky

Milos Ivkovic

Ching-Fu Wu

Dongwoon Bai

Joachim S Hammerschmdit

Nirav P Dave

Wenwei Pan

Kiran Gunman

Methods and apparatus are provided for processing a data value in a read channel of a memory device. The data value provided to a general purpose processor for processing. The data value is not decoded data and may comprise one or more of a raw data value and an intermediate data value. The data value can be provided to the general purpose processor, for example, upon a detection of one or more predefined trigger conditions. A data value can be obtained from a memory device and then be redirected to a general purpose processor. The data value is not decoded data. The redirection can be conditionally performed if one or more predefined bypass conditions exist. The general purpose processor is optionally time-shared with one or more additional applications.

Memory read-channel with signal processing on general purpose processor

A hard input low density parity check decoder is provided that shares logic between a bit-flipping decoder and a syndrome calculator. The hard-decision decoder decodes one or more error-correcting (EC) codewords and comprises a bit-flipping decoder that flips one or more bit nodes connected to one or more unsatisfied parity checks; and a syndrome calculator that performs a parity check to determine whether the bit-flipping decoder has converged on a valid codeword, wherein the bit-flipping decoder and the syndrome calculator share one or more logic elements. The decoder optionally includes means for updating a parity check equation of each flipped bit. Error-correcting (EC) codewords are decoded by flipping one or more bit nodes connected to one or more unsatisfied parity checks; and updating one or more parity check equations associated with the one or more bit nodes each time the one or more bit nodes are flipped. The parity check equations are updated whenever a bit is updated. The exemplary method terminates based on a predefined syndrome output.

Hard input low density parity check decoder

In one embodiment, the present invention is a variable node unit (VNU) of a low-density parity-check (LDPC) decoder. The VNU receives a soft-input value and wcheck node messages, where wis the column hamming weight of the LDPC code. The VNU generates (i) an extrinsic log-likelihood ratio (LLR) by adding all wcheck node messages together; (ii) a hard-decision output by adding the extrinsic LLR to the soft-input value and selecting the sign bit of the resulting sum; and (iii) wvariable node messages. Each variable node message is generated by adding a different set of (w&#x2212;1) check node messages to the soft-input value where each set excludes a different check node message. In so doing, VNUs of the present invention may generate variable node messages using fewer adder stages compared to prior-art VNUs such that throughput may be increased over that of prior-art VNUs.

LDPC decoder variable node units having fewer adder stages

A memory read-channel is provided with selective transmission of error correction data. The disclosed read-channel improves throughput and reduces power consumption when error correction codes are unnecessary. The data read from a memory device comprises user data, error detection data and error correction data. In one embodiment, the error detection data is evaluated to determine if there is a data error; and the error correction data is transmitted only if a data error is detected. In another variation, the error detection data is evaluated during data transmission to determine if there is a data error and the transmission is suspended if a data error is detected. Typically, the error detection data comprises a cyclic redundancy check and the error correction data comprises parity check data.

Memory read-channel with selective transmission of error correction data

Methods and apparatus are provided for intercell interference mitigation using modulation coding. During programming of a flash memory, a modulation encoding is performed that selects one or more levels for programming the flash memory such that a reduced number of cells in the flash memory are programmed with a value that violates one or more predefined criteria. During a reading of a flash memory, a modulation decoding is performed that assigns one or more levels to cells in the flash memory such that a reduced number of cells in the flash memory are read with a value that violates one or more predefined criteria. The predefined criteria can be based, for example, on one or more of an amount of disturbance caused by the programmed cell; a voltage shift of a programmed cell: a voltage stored by a programmed cell; an amount of change in current through a programmed cell; and an amount of current through a programmed cell.

Methods and apparatus for intercell interference mitigation using modulation coding

In one embodiment, a signal-processing receiver has an upstream processor and a low-density parity-check (LDPC) decoder for decoding LDPC-encoded codewords. The upstream processor generates a soft-output value for each bit of the received codewords. The LDPC decoder is implemented to process the soft-output values without having to wait until all of the soft-output values are generated for the current codeword. Further, the LDPC code used to encode the codewords is arranged to support such processing. By processing the soft-output values without having to wait until all of the soft-output values are generated for the current codeword, receivers of the present invention may have a lower latency and higher throughput than prior-art receivers that wait until all of the soft-output values are generated prior to performing LDPC decoding. In another embodiment, the LDPC decoder processes the soft-output values as soon as, and in the order that, they are generated.

Low-latency decoder

Various embodiments of the present invention provide systems and methods for determining fly height.

Systems and methods for variable compensated fly height measurement

Executed when a channel input (e.g., LDPC) codeword is written to a storage medium, a write-verification method (i) compares the channel input codeword to the written codeword, (ii) identifies any erroneous bits, and (iii) stores the erroneous-bit indices to a record in a table. At some later time, the written codeword is read and sent to a decoder. If the decoder fails with a near codeword, a write-error recovery process searches the table and retrieves the erroneous-bit information. The codeword bits at those indices are adjusted, and the modified codeword is submitted to further processing.

Error-floor mitigation of codes using write verification

A survivor path memory is provided for a Viterbi detector. The survivor path memory comprises a plurality of columns, each associated with a different time step, and an input processor. Each column comprises a flip flop for storing one bit or portion of a bit sequence associated with a Viterbi state; and a multiplexer for each state controlled by a case signal indicating a time step, the multiplexer selecting a state from a previous time step, wherein an output of the multiplexer of a given state is connected to at least one data input of a flip flop of the given state. The input processor generates a control signal that exchanges one or more pointers based on a trellis structure, wherein each of the pointers points to one of the flip flops.

Method and apparatus for storing survivor paths in a viterbi detector using systematic pointer exchange

A stabilized quadrature oscillator providing consistently high signal quality is disclosed. The stabilized quadrature oscillator includes an iterative quadrature oscillator and a quadrature signal stabilizer. The iterative quadrature oscillator generates an iterative cosine signal and an iterative sine signal using a stabilized cosine signal and a stabilized sine signal from the quadrature signal stabilizer. The quadrature signal stabilizer generates the stabilized cosine signal and the stabilized sine signal based on an energy measure of the iterative cosine signal and the iterative sine signal. Specifically, if the energy measure is less than a low threshold then the quadrature signal stabilizer generates the stabilized sine signal and the stabilized cosine signal to have a greater magnitude than the iterative sine signal and the iterative cosine signal, respectively. Conversely, if the energy measure is greater than a high threshold then the quadrature signal stabilizer generates the stabilized sine signal and the stabilized cosine signal to have a lesser magnitude than the iterative sine signal and the iterative cosine signal, respectively.

Stabilized digital quadrature oscillator

A processor circuit having reduced power consumption includes an analog front end operative to receive an analog signal supplied to the processor circuit and to generate a digital signal indicative of the analog signal. The processor further includes a digital back end operative to generate a digital output signal as a function of the digital signal generated by the analog front end. A buffer is coupled between the analog front end and the digital back end. In a first mode of operation, the digital back end operates at a substantially same data rate as the analog front end and the buffer is bypassed. In a second mode of operation, the digital back end operates at a higher data rate than the analog front end and the buffer is used to store outputs of the analog front end.

Turning off buffer when a digital back end operates at a same data rate as the analog front end

Various embodiments of the present invention provide systems and methods for data processing. For example, a variable iteration data processing system is disclosed that includes a first detector, a second detector, a decoder and a unified memory buffer. An input data set is received by the first detector that performs a data detection and provides a first detected data set. The decoder receives a derivative of the first detected data set and performs a decoding operation that yields a decoded data set. In some cases, the derivative of the first detected data set is an interleaved version of the first detected data set. The decoded data set is written to a unified memory buffer. The first decoded data set is retrievable from the unified memory buffer and a derivative thereof is provided to the second detector. In some cases, the derivative of the decoded is a de-interleaved version of the decoded data set. The second detector is operable to perform a data detection on the derivative of the decoded data set and to provide a second detected data set that is written to the unified memory buffer.

Power reduced queue based data detection and decoding systems and methods for using such

In one embodiment, an LDPC decoder has a plurality of check-node units (CNUs) and a controller. Initially, the CNUs generate check-node messages based on an initial offset value selected by the controller. If the decoder converges on a trapping set, then the controller selects new offset values for missatisfied check nodes (MSCs), the locations of which are approximated, and/or unsatisfied check nodes (USCs). In particular, offset values are selected such that (i) the messages corresponding to the MSCs are decreased relative to the messages that would be generated using the initial offset value and/or (ii) the messages corresponding to the USCs are increased relative to the messages that would be generated using the initial offset value. Decoding is then continued for a specified number of iterations to break the trapping set. In other embodiments, the controller selects scaling factors rather than, or in addition to, offset values.

Selectively strengthening and weakening check-node messages in error-correction decoders

Various embodiments of the present invention provide systems and methods for LDPC encoding and decoding. For example, a system for performing LDPC encoding and decoding is disclosed that includes a joint LDPC encoder/decoder. The joint LDPC encoder/decoder includes both an LDPC decoder and an LDPC encoder that each utilize a common LDPC decoder circuit to perform the respective functions of encoding and decoding.

Systems and methods for joint LDPC encoding and decoding

In one embodiment, the present invention is a low-density parity-check (LDPC) decoder that has a plurality of variable node units (VNUs) that generate variable node messages and a plurality of check node units (CNUs) that generate check node messages. The variable node messages and check node messages are distributed between the VNUs and CNUs using a number r of combinations of permutators, wherein each permutator combination includes (i) a cyclic shifter and (ii) a fixed, non-cyclic permutator. The cyclic shifters are capable of supporting a number p of different cyclic LDPC sub-matrices; however, when combined with different fixed permutators, the permutator combinations are capable of supporting up to r&#xd7;p different LDPC sub-matrices. In other embodiments, the LDPC decoder may have fewer than r fixed permutators such that the LDPC decoder is capable of supporting between p and r&#xd7;p different LDPC sub-matrices.

Growing community of inventors

Milpitas, CA, United States of America

Nils Graef