Abstract: An apparatus for reading a non-volatile memory includes a tracking module operable to calculate means and variances of voltage level distributions in a non-volatile memory and to calculate at least one reference voltage to be used when reading the non-volatile memory based on the means and variances, a likelihood generator operable to calculate at least one other reference voltage to be used when reading the non-volatile memory, wherein the at least one other reference voltage is based at least in part on a predetermined likelihood value constellation, and to map read patterns from the non-volatile memory to likelihood values, and a read controller operable to read the non-volatile memory using the at least one reference voltage and the at least one other reference voltage to yield the read patterns.

Abstract: An indication of a page type which failed error correction decoding is received. A threshold to adjust is selected from a plurality of thresholds based at least in part on the page type. A third adjusted threshold associated with the page type is generated, including by: determining a first number of flipped bits using a first adjusted threshold associated with the page type, determining a second number of flipped bits using a second adjusted threshold associated with the page type, and generating the third adjusted threshold using the first number of flipped bits and the second number of flipped bits.

Abstract: An input file is processed according to hash algorithm that references sets of literals to preceding sets of literals to facilitate copy-offset command generation. Preceding instances are identified by generating a hash of the literal set and looking up a corresponding entry in a hash table. The hash table may be accessed by placing look-up requests in a FIFO buffer. When the FIFO buffer is full, generation of the hash chain is suspended until it is no longer full. When repeated literals are found, generation of the hash chain is likewise suspended. The hash chain is used to generate a command file, such as according to the LZ algorithm. Runs of consecutive literals are replaced by a run-length command. The command file may then be encoded using Huffman encoding.

Abstract: A compression algorithm replaces duplicative strings with a copy pair indicating a location and length of a preceding identical string that is within a window from the duplicative string. Rather than a replacing a longest matching string within a window from a given point with a copy pair, the longest matching string may be used provide it is at least two bytes larger than the next longest matching string or is at a distance that is less than some multiple of a distance to the next longest matching string. In another aspect, the length of the window in which a matching string may be found is dependent on a length of the matching string. In yet another aspect, rather than labeling each literal and copy pair to indicate what it is, strings of non-duplicative literals are represented by a label and a length of the string.

Abstract: A method is disclosed for performing LDPC soft decoding of data stored in a flash storage device. Upon occurrence of a hard read failure, one or more retries with soft decoding after each retry are performed until soft decoding is successful or a maximum iteration count is reached. For each retry thresholds for sensing a level of a cell are adjusted according to a specific sequence. Likewise, the LLR table for each retry is selected from pre-determined LLR tables each corresponding to a retry attempt and the thresholds used for the retry attempt. The LLR table is not adjusted between retries or based on outcomes of any retries. A step size by which thresholds adjusted may be tuned to improve performance.

Abstract: A compression algorithm based on Huffman coding is disclosed that is adapted to be readily implemented using VLSI design. A data file may be processed to replace duplicate data with a copy commands including an offset and length, such as according to the LV algorithm. A Huffman code may then be generated for parts of the file. The Huffman code may be generated according to a novel method that generates Huffman code lengths for literals in a data file without first sorting the literal statistics. The Huffman code lengths may be constrained to be no longer than a maximum length and the Huffman code may be modified to provide an acceptable overflow probability and be in canonical order. Literals, offsets, and lengths may be separately encoded. The different values for these data sets may be assigned to a limited number of bins for purpose of generating usage statistics used for generating Huffman codes.

Abstract: An apparatus for reading a non-volatile memory includes a tracking module operable to calculate means and variances of voltage level distributions in a non-volatile memory and to calculate at least one reference voltage to be used when reading the non-volatile memory based on the means and variances, a likelihood generator operable to calculate at least one other reference voltage to be used when reading the non-volatile memory, wherein the at least one other reference voltage is based at least in part on a predetermined likelihood value constellation, and to map read patterns from the non-volatile memory to likelihood values, and a read controller operable to read the non-volatile memory using the at least one reference voltage and the at least one other reference voltage to yield the read patterns.

Abstract: A compression algorithm replaces duplicative strings with a copy pair indicating a location and length of a preceding identical string that is within a window from the duplicative string. Rather than a replacing a longest matching string within a window from a given point with a copy pair, the longest matching string may be used provide it is at least two bytes larger than the next longest matching string or is at a distance that is less than some multiple of a distance to the next longest matching string. In another aspect, the length of the window in which a matching string may be found is dependent on a length of the matching string. In yet another aspect, rather than labeling each literal and copy pair to indicate what it is, strings of non-duplicative literals are represented by a label and a length of the string.

Abstract: Methods and apparatus are provided for integrated-interleaved Low Density Parity Check (LDPC) coding and decoding. Integrated-interleaved LDPC encoding is performed by obtaining at least a first data element and a second data element; systematically encoding the at least first data element using a submatrix H0 of a sparse parity check matrix H1 to obtain at least a first codeword; truncating the at least first data element to obtain at least a first truncated data element; systematically encoding the at least second data element and the at least first truncated data element using the sparse parity check matrix H1 to obtain a nested codeword; and generating a second codeword based at least in part on a combination of the first codeword and the nested codeword. Integrated-interleaved LDPC decoding is also provided.

Abstract: An SSD controller dynamically adjust read thresholds in a NVM to reduce errors due to device threshold voltage distribution shifts, thus improving performance, reliability, and/or cost of a storage sub-system, such as an SSD. In a first aspect, the controller periodically performs offline tracking on a portion of the NVM. The controller reads a representative sub-portion with current read thresholds. If the read meets a condition, then the controller reads the sub-portion with sample read thresholds, estimates the device threshold voltage distributions, and adjusts the current read thresholds of the portion to calculated new operating read thresholds of the sub-portion. In a second aspect, the portion includes data with a known statistical average number of zero and/or one bits.

Abstract: An instruction to write to a location in the Flash memory is received. It is determining if the Flash memory exposes a level placement setting associated with defining what voltage range corresponds to what level. In the event it is determined that the Flash memory exposes a level placement setting, an accurate coarse write is performed on the location, including by configuring the level placement setting to be a first value, and after the accurate coarse write is performed on the location, a fine write is performed on the location, including by configuring the level placement setting to be a second value, in response to receiving the instruction.

Abstract: An instruction to write to a location in the Flash memory is received. It is determining if the Flash memory exposes a level placement setting associated with defining what voltage range corresponds to what level. In the event it is determined that the Flash memory exposes a level placement setting, an accurate coarse write is performed on the location, including by configuring the level placement setting to be a first value, and after the accurate coarse write is performed on the location, a fine write is performed on the location, including by configuring the level placement setting to be a second value, in response to receiving the instruction.

Abstract: Methods and apparatus are provided for integrated-interleaved Low Density Parity Check (LDPC) coding and decoding. Integrated-interleaved LDPC encoding is performed by obtaining at least a first data element and a second data element; systematically encoding the at least first data element using a submatrix H0 of a sparse parity check matrix H1 to obtain at least a first codeword; truncating the at least first data element to obtain at least a first truncated data element; systematically encoding the at least second data element and the at least first truncated data element using the sparse parity check matrix H1 to obtain a nested codeword; and generating a second codeword based at least in part on a combination of the first codeword and the nested codeword. Integrated-interleaved LDPC decoding is also provided.

Abstract: A compression algorithm is disclosed in which compressibility of an input frame is determined. If a frame is found to be compressible, it is input to a compression algorithm, otherwise the frame may bypass the compression algorithm. Literals of length N bits in a frame are sorted into 2^N bins such a counter Bi indicates a number of literals of value i. The maximum and minimum counter values are evaluated to estimate the compressibility of the file. For example, if Bmax is the maximum counter value and Bmin is the minimum counter value, then If Bmax<A*Bmin (A being a value greater than 1, e.g. 4), the frame may be deemed to be uncompressible, otherwise the frame may be deemed to be compressible and compressed according to the DEFLATE algorithm or some other compression algorithm.

Abstract: An indication of a page type which failed error correction decoding is received. A threshold to adjust is selected from a plurality of thresholds based at least in part on the page type. A third adjusted threshold associated with the page type is generated, including by: determining a first number of flipped bits using a first adjusted threshold associated with the page type, determining a second number of flipped bits using a second adjusted threshold associated with the page type, and generating the third adjusted threshold using the first number of flipped bits and the second number of flipped bits.

Abstract: An apparatus for reading a non-volatile memory includes a tracking module operable to calculate means and variances of voltage level distributions in a non-volatile memory and to calculate at least one reference voltage to be used when reading the non-volatile memory based on the means and variances, a likelihood generator operable to calculate at least one other reference voltage to be used when reading the non-volatile memory, wherein the at least one other reference voltage is based at least in part on a predetermined likelihood value constellation, and to map read patterns from the non-volatile memory to likelihood values, and a read controller operable to read the non-volatile memory using the at least one reference voltage and the at least one other reference voltage to yield the read patterns.

Abstract: A method and system for constructing a generator matrix is disclosed. The method includes: receiving a parity check matrix H, wherein the parity check matrix H includes multiple circulant sub-matrices; rearranging the parity check matrix H by column and row permutations to obtain a rearranged parity check matrix H?; and constructing the generator matrix G based on the rearranged parity check matrix H?.

Abstract: A method of optimizing solid state drive (SSD) soft retry voltages comprises limiting a number of voltage reads and properly spacing and determining the reference voltage at which each voltage is read based on desired Bit Error Rate (BER) and channel throughput. The method determines each reference voltage for a number of soft retry voltage reads based on a hard decision read. The spacing between each read reference voltage is constant since each SSD type requires a number of reads for an accurate presentation of soft retry voltages. The voltage distance between each successive read is limited to a multiple of the constant spacing while the multiple is based on success or failure of the first read. The method determines a limited number of reads, the constant spacing between reads, and a desired reference voltage for each read, thereby increasing valuable throughput of the channel and decreasing BER.

Abstract: Methods and apparatus are provided for integrated-interleaved Low Density Parity Check (LDPC) coding and decoding. Integrated-interleaved LDPC encoding is performed by obtaining at least a first data element and a second data element; systematically encoding the at least first data element using a submatrix H0 of a sparse parity check matrix H1 to obtain at least a first codeword; truncating the at least first data element to obtain at least a first truncated data element; systematically encoding the at least second data element and the at least first truncated data element using the sparse parity check matrix H1 to obtain a nested codeword; and generating a second codeword based at least in part on a combination of the first codeword and the nested codeword. Integrated-interleaved LDPC decoding is also provided.

Abstract: An instruction to write to a location in the Flash memory is received. It is determining if the Flash memory exposes a level placement setting associated with defining what voltage range corresponds to what level. In the event it is determined that the Flash memory exposes a level placement setting, an accurate coarse write is performed on the location, including by configuring the level placement setting to be a first value, and after the accurate coarse write is performed on the location, a fine write is performed on the location, including by configuring the level placement setting to be a second value, in response to receiving the instruction.