| Patent application number | Description | Published |
|---|
| 20080215798 | Randomizing for suppressing errors in a flash memory - Original data to be stored in a nonvolatile memory are first randomized while preserving the size of the original data, In response for a request for the original data, the randomized data are retrieved, derandomized and exported without authenticating the requesting entity. ECC encoding is applied either before or after randomizing; correspondingly, ECC decoding is applied either after or before derandomizing. | 09-04-2008 |
| 20080263265 | ADAPTIVE DYNAMIC READING OF FLASH MEMORIES - Each of a plurality of flash memory cells is programmed to a respective one of L≧2 threshold voltage states within a threshold voltage window. Values of parameters of threshold voltage functions are adjusted in accordance with comparisons of the threshold voltages of some or all of the cells to two or more of m≧2 threshold voltage intervals within the threshold voltage window. Reference voltages for reading the cells are selected based on the values. Alternatively, the m threshold voltage intervals span the threshold voltage window, and respective threshold voltage states are assigned to the cells based on numbers of cells whose threshold voltages are in the intervals, without re-reading the cells. | 10-23-2008 |
| 20080263266 | ADAPTIVE DYNAMIC READING OF FLASH MEMORIES - Each of a plurality of flash memory cells is programmed to a respective one of L≧2 threshold voltage states within a threshold voltage window. A histogram is constructed by determining how many of some or all of the cells have threshold voltages in each of two or more of m≧2 threshold voltage intervals within the threshold voltage window. Reference voltages for reading the cells are selected based on estimated values of shape parameters of the histogram. Alternatively, the cells are read relative to reference voltages that define m≧2 threshold voltage intervals that span the threshold voltage window, to determine numbers of at least a portion of the cells whose threshold voltages are in each of two or more of the threshold voltage intervals. Respective threshold voltage states are assigned to the cells based on the numbers without re-reading the cells. | 10-23-2008 |
| 20080291724 | MULTI-BIT-PER-CELL FLASH MEMORY DEVICE WITH NON-BIJECTIVE MAPPING - To store a plurality of input bits, the bits are mapped to a corresponding programmed state of one or more memory cells and the cell(s) is/are programmed to that corresponding programmed state. The mapping may be many-to-one or may be an “into” generalized Gray mapping. The cell(s) is/are read to provide a read state value that is transformed into a plurality of output bits, for example by maximum likelihood decoding or by mapping the read state value into a plurality of soft bits and then decoding the soft bits. | 11-27-2008 |
| 20090070657 | METHOD OF ERROR CORRECTION IN MBC FLASH MEMORY - A plurality of logical pages is stored in a MBC flash memory along with corresponding ECC bits, with at least one of the MBC cells storing bits from more than one logical page, and with at least one of the ECC bits applying to two or more of the logical pages. When the pages are read from the memory, the data bits as read are corrected using the ECC bits as read. Alternatively, a joint, systematic or non-systematic ECC codeword is computed for two or more of the logical pages and is stored instead of those logical pages. When the joint codeword is read, the logical bits are recovered from the codeword as read. The scope of the invention also includes corresponding memory devices, the controllers of such memory devices, and also computer-readable storage media bearing computer-readable code for implementing the methods. | 03-12-2009 |
| 20090183049 | PROBABILISTIC ERROR CORRECTION IN MULTI-BIT-PER-CELL FLASH MEMORY - Data that are stored in cells of a multi-bit-per cell memory, according to a systematic or non-systematic ECC, are read and corrected (systematic ECC) or recovered (non-systematic ECC) in accordance with estimated probabilities that one or more of the read bits are erroneous. In one method of the present invention, the estimates are a priori. In another method of the present invention, the estimates are based only on aspects of the read bits that include significances or bit pages of the read bits. In a third method of the present invention, the estimates are based only on values of the read bits. Not all the estimates are equal. | 07-16-2009 |
| 20090217131 | PROBABILISTIC ERROR CORRECTION IN MULTI-BIT-PER-CELL FLASH MEMORY - Data that are stored in cells of a multi-bit-per cell memory, according to a systematic or non-systematic ECC, are read and corrected (systematic ECC) or recovered (non-systematic ECC) in accordance with estimated probabilities that one or more of the read bits are erroneous. In one method of the present invention, the estimates are a priori. In another method of the present invention, the estimates are based only on aspects of the read bits that include significances or bit pages of the read bits. In a third method of the present invention, the estimates are based only on values of the read bits. Not all the estimates are equal. | 08-27-2009 |
| 20090319722 | AD HOC FLASH MEMORY REFERENCE CELLS - In a nonvolatile memory, that includes cells organized in a plurality of bit lines and a plurality of word lines, user data are stored in respective portions of each of two of the word lines. Control information is stored in a cell that is common to one of the bit lines and one of the two word lines. A cell that is common to the bit line and the other word line is used as a reference cell. A flash memory, that includes a plurality of primary cells and a plurality of spare cells, is interrogated to determine which spare cells have been used to replace respective primary cells. At least some of the other spare cells are used as reference cells. | 12-24-2009 |
| 20090319858 | REDUCED COMPLEXITY LDPC DECODER - To decode a manifestation of a codeword in which K information bits are encoded as N>K codeword bits, messages are exchanged between N bit nodes and N−K check nodes. During computation, messages are expressed with a full message length greater than two bits. In each iteration, representations of at least some of the exchanged messages are stored. For at least one node, if representations of messages sent from that node are stored, then the representation of one or more of the messages is stored using at least two bits but using fewer bits than the full message length, and the representation of one other message is stored with full message length. Preferably, the messages that are stored using fewer bits than the full message length are messages sent from check nodes. | 12-24-2009 |
| 20090319859 | METHOD AND APPARATUS FOR ERROR CORRECTION ACCORDING TO ERASE COUNTS OF A SOLID-STATE MEMORY - Embodiments of the present invention relate to methods and devices where an erase count is maintained for at least one block of solid state memory. Errors are corrected in data read from the solid state memory in accordance with the associated erase count of the memory block. In some embodiments, one or more of the following error-correction operations may be effected according to the associated erase count of a memory block from which the data is read: (i) a decoder and/or decoder mode is selected; (ii) a decision to attempt correcting errors using a lighter-weight weight decoder (mode) and/or heavier weight decoder (mode) and/or faster decoder (mode) and/or slower decoder (mode) is made; (iii) a mode transition and/or error correction attempt resource budget is determined; (iv) a number of soft bits is determined; and (v) a decoding bus width size is selected. | 12-24-2009 |
| 20090319860 | OVERCOMING LDPC TRAPPING SETS BY DECODER RESET - To decode, in a plurality of iterations, a representation, imported from a channel, of a codeword that encodes K information bits as N>K codeword bits, estimates of the codeword bits are updated by exchanging messages between N bit nodes and N−K check nodes of a graph. If the decoding has failed to converge according to a predetermined failure criterion and if the codeword bit estimates satisfy a criterion symptomatic of the graph including a trapping set, at least a portion of the messages are reset before continuing the iterations. Alternatively, if the decoding fails to converge according to a predetermined failure criterion, at least a portion of the messages that are sent from the bit nodes are truncated before continuing the iterations. | 12-24-2009 |
| 20090319861 | USING DAMPING FACTORS TO OVERCOME LDPC TRAPPING SETS - To decode a representation, imported from a channel, of a codeword that encodes K information bits as N>K codeword bits, estimates of the codeword bits are updated by exchanging messages between N bit nodes and N−K check nodes of a graph in a plurality of iterations. In each of one or more of the iterations, some or all values associated with the bit nodes, and/or some or all values associated with check nodes, and/or some or all messages are modified in a manner that depends explicitly on the ordinality of the iteration and is independent of any other iteration. Alternatively, the modifications are according to respective locally heteromorphic rules. | 12-24-2009 |
| 20090319868 | READING A FLASH MEMORY BY JOINT DECODING AND CELL VOLTAGE DISTRIBUTION TRACKING - To read a plurality of memory cells, each cell is assigned to a respective cell population. A respective value of an operational parameter of each cell is measured. Each cell is assigned an a-priori metric based at least in part on one or more CVD parameter values of the cell's population. The a-priori metrics are decoded. Based at least in part on the resulting a-posteriori metrics, the CVD parameter values are corrected, without repeating the measurements of the cell operational parameter values. The operational parameter values are indicative of bit patterns stored in the cells, and the correction of the CVD parameter values is constrained by requiring the bit patterns collectively to be a valid codeword. | 12-24-2009 |
| 20090323422 | GAIN CONTROL FOR READ OPERATIONS IN FLASH MEMORY - A technique for performing read operations with reduced errors in a memory device such as flash memory. An automatic gain control approach is used in which cells which have experienced data retention loss are read by a fine M-level quantizer which uses M-1 read threshold voltage levels. In one approach, M-quantized threshold voltage values are multiplied by a gain to obtain gain-adjusted threshold voltage values, which are quantized by an L-level quantizer, where L| 12-31-2009 | |
| 20090323942 | METHOD FOR PAGE- AND BLOCK BASED SCRAMBLING IN NON-VOLATILE MEMORY - A method and system for programming and reading data with reduced read errors in a memory device. In one approach, date to be written to the memory device is scrambled using a first pseudo random number which is generated based on a page of the memory device to which the data is to be written, to provide first scrambled data, which is scrambled using a second pseudo random number which is generated based on a block of the memory device to which the data is to be written. This avoids bit line-to-bit line and block-to-block redundancies which can result in read errors. The data may also be scrambled using a third pseudo random number that depends on a section within a page. Scrambling may also be based on one or more previous pages which were written. | 12-31-2009 |
| 20090327841 | PROBABILISTIC ERROR CORRECTION IN MULTI-BIT-PER-CELL FLASH MEMORY - Data that are stored in cells of a multi-bit-per cell memory, according to a systematic or non-systematic ECC, are read and corrected (systematic ECC) or recovered (non-systematic ECC) in accordance with estimated probabilities that one or more of the read bits are erroneous. In one method of the present invention, the estimates are a priori. In another method of the present invention, the estimates are based only on aspects of the read bits that include significances or bit pages of the read bits. In a third method of the present invention, the estimates are based only on values of the read bits. Not all the estimates are equal. | 12-31-2009 |
| 20100005367 | PROBABILISTIC ERROR CORRECTION IN MULTI-BIT-PER-CELL FLASH MEMORY - Data that are stored in cells of a multi-bit-per cell memory, according to a systematic or non-systematic ECC, are read and corrected (systematic ECC) or recovered (non-systematic ECC) in accordance with estimated probabilities that one or more of the read bits are erroneous. In one method of the present invention, the estimates are a priori. In another method of the present invention, the estimates are based only on aspects of the read bits that include significances or bit pages of the read bits. In a third method of the present invention, the estimates are based only on values of the read bits. Not all the estimates are equal. | 01-07-2010 |
| 20100005370 | PROBABILISTIC ERROR CORRECTION IN MULTI-BIT-PER-CELL FLASH MEMORY - Data that are stored in cells of a multi-bit-per cell memory, according to a systematic or non-systematic ECC, are read and corrected (systematic ECC) or recovered (non-systematic ECC) in accordance with estimated probabilities that one or more of the read bits are erroneous. In one method of the present invention, the estimates are a priori. In another method of the present invention, the estimates are based only on aspects of the read bits that include significances or bit pages of the read bits. In a third method of the present invention, the estimates are based only on values of the read bits. Not all the estimates are equal. | 01-07-2010 |
| 20100070692 | MULTI-BIT-PER-CELL FLASH MEMORY DEVICE WITH NON-BIJECTIVE MAPPING - To store a plurality of input bits, the bits are mapped to a corresponding programmed state of one or more memory cells and the cell(s) is/are programmed to that corresponding programmed state. The mapping may be many-to-one or may be an “into” generalized Gray mapping. The cell(s) is/are read to provide a read state value that is transformed into a plurality of output bits, for example by maximum likelihood decoding or by mapping the read state value into a plurality of soft bits and then decoding the soft bits. | 03-18-2010 |
| 20100082885 | METHOD AND SYSTEM FOR ADAPTIVE CODING IN FLASH MEMORIES - Bits are stored by attempting to set parameter value(s) of (a) cell(s) to represent some of the bits. In accordance with the attempt, an adaptive mapping of the bits to value ranges is provided and the value(s) is/are adjusted accordingly as needed. Or, to store (a) bit(s) in (a) cell(s), a default mapping of the bit(s) to a predetermined set of value ranges is provided and an attempt is made to set the cell value(s) accordingly. If, for one of the cells, the attempt sets the value such that the desired range is inaccessible, an adaptive mapping is provided such that the desired range is accessible. Or, to store (a) bit(s) in (a) cell(s), several mappings of the bit(s) to a predetermined set of ranges is provided. Responsive to an attempt to set the cell value(s) according to one of the mappings, the mapping to actually use is selected. | 04-01-2010 |
| 20100088575 | LOW DENSITY PARITY CODE (LDPC) DECODING FOR MEMORY WITH MULTIPLE LOG LIKELIHOOD RATIO (LLR) DECODERS - Data stored in memory is decoded using iterative probabilistic decoding and multiple decoders. A first decoder attempts to decode a representation of a codeword. If the attempt is unsuccessful, a second decoder attempts to decode the representation of a codeword. The second decoder may have a lower resolution than the first decoder. Probability values such as logarithmic likelihood ratio (LLR) values may be clipped in the second decoder. This approach can overcome trapping sets while exhibiting low complexity and high performance. Further, it can be implemented on existing decoders such as those used in current memory devices. | 04-08-2010 |
| 20100131697 | METHODS FOR TAG-GROUPING OF BLOCKS IN STORAGE DEVICES - Embodiments described herein disclose methods, devices, and media for storing data. Methods including the steps of: receiving data to be stored in a memory that includes at least three blocks, wherein each block, for storing the data, has at least one metadata value, associated with each block, that is dependent upon a writing time of each block; grouping at least three blocks into at least two block groups, wherein at least one block group contains at least two blocks; associating a respective metadata value with each block group; and associating the respective metadata value of a respective block group with each block storing the data contained in the respective block group, without storing a dedicated copy of at least one metadata value for each block. In some embodiments, at least one metadata value is stored in a block-group table. | 05-27-2010 |
| 20100169737 | METHOD AND DEVICE FOR MULTI PHASE ERROR-CORRECTION - Data bits to be encoded are split into a plurality of subgroups. Each subgroup is encoded separately to generate a corresponding codeword. Selected subsets are removed from the corresponding codewords, leaving behind shortened codewords, and are many-to-one transformed to condensed bits. The final codeword is a combination of the shortened codewords and the condensed bits. A representation of the final codeword is decoded by being partitioned to a selected subset and a plurality of remaining subsets. Each remaining subset is decoded separately. If one of the decodings fails, the remaining subset whose decoding failed is decoded at least in part according to the selected subset. If the encoding and decoding are systematic then the selected subsets are of parity bits. | 07-01-2010 |
| 20100192042 | READING A FLASH MEMORY BY CONSTRAINED DECODING - To read memory cells that have been programmed to store an ECC codeword, with each cell storing a respective plurality of bits of the codeword, a respective value of an operational parameter such as a threshold voltage of each cell is measured. Each bit is assigned a respective metric, such as a LLR estimate of the bit, based at least in part on the respective value of the operational parameter of the bit's cell. The metrics are decoded with reference both to the ECC and to mutual constraints of the metrics within each cell that are independent of the ECC. | 07-29-2010 |
| 20100192043 | INTERRUPTION CRITERIA FOR BLOCK DECODING - While decoding a representation, imported from a channel, of a codeword that encodes K information bits as N>K codeword bits, by updating estimates of the codeword bits in a plurality of iterations, the iterations are interrupted upon satisfaction of an interruption criterion that is either an order-dependent interruption criterion or an interruption criterion that includes an estimate of mutual information of the codeword and a vector that is used in the decoding iterations. Either the iterations are terminated or the iterations are resumed after one or more elements of one or more vectors used in the iterations is/are modified. | 07-29-2010 |
| 20100195384 | SYSTEM AND METHOD TO READ DATA SUBJECT TO A DISTURB CONDITION - Systems and methods for reading data are disclosed. In a particular embodiment, a method includes measuring characteristics of a plurality of cells at a memory. The characteristics correspond to a plurality of values including a first value stored at a particular cell and a second value stored at a second cell of the memory. The method includes testing whether at least some of the plurality of values match a particular pattern correlated to a disturb condition at the particular cell, and providing a data value corresponding to the particular cell. The data value is determined at least in part based on a result of the testing. | 08-05-2010 |
| 20100287440 | MATRIX STRUCTURE FOR BLOCK ENCODING - A plurality of information bits are encoded using a parity-check matrix that is equivalent to a modular code matrix. The modular code matrix is a diagonal sub-matrix structure immediately above a connection layer that includes a plurality of diverse connection layer sub-matrices, all but at most one of which are below corresponding diagonal matrix structure sub-matrices. The information bits are assembled with a plurality of parity bits produced by the encoding to provide a codeword that is exported to a medium. Preferably, all the diagonal matrix structure sub-matrices are identical. Preferably, some of the parity bits are computed using only diagonal matrix structure sub-matrices. | 11-11-2010 |
| 20100332729 | MEMORY OPERATIONS USING LOCATION-BASED PARAMETERS - Systems and methods of performing memory operations using location-based parameters are disclosed. A method includes identifying a first set of parameter values associated with a first physical block of a memory array. The first set of parameter values is identified based on a first physical location of the first physical block. A memory access operation is initiated with respect to the first physical block in accordance with the first set of parameter values. | 12-30-2010 |
| 20100332956 | POLYNOMIAL DIVISION - Systems and methods to perform polynomial division are disclosed. In a particular embodiment, the method includes receiving a codeword and storing a portion of the received codeword at a register. The portion of the received codeword has a first number of terms. A divisor having a second number of terms is also received. During at least one stage of a multi-stage polynomial division operation using the portion of the codeword and the divisor, the portion of the received codeword to be divided by the divisor is adjusted based on a result of a comparison of the first number to the second number. | 12-30-2010 |
| 20110007573 | GAIN CONTROL FOR READ OPERATIONS IN FLASH MEMORY - A technique for performing read operations with reduced errors in a memory device such as flash memory. An automatic gain control approach is used in which cells which have experienced data retention loss are read by a fine M-level quantizer which uses M-1 read threshold voltage levels. In one approach, M-quantized threshold voltage values are multiplied by a gain to obtain gain-adjusted threshold voltage values, which are quantized by an L-level quantizer, where L| 01-13-2011 | |
| 20110022920 | COMPACT DECODING OF PUNCTURED BLOCK CODES - k input bits are encoded according to a code with which is associated a m×n=m+k parity check matrix H. The resulting codeword is punctured, with n′| 01-27-2011 | |
| 20110022921 | COMPACT DECODING OF PUNCTURED BLOCK CODES - k input bits are encoded according to a code with which is associated a m×n=m+k parity check matrix H. The resulting codeword is punctured, with n′| 01-27-2011 | |
| 20110022922 | COMPACT DECODING OF PUNCTURED BLOCK CODES - k input bits are encoded according to a code with which is associated a m×n=m+k parity check matrix H. The resulting codeword is punctured, with n′| 01-27-2011 | |
| 20110022927 | COMPACT DECODING OF PUNCTURED CODES - k information bits are encoded according to a code with which is associated a parity check matrix H that has n columns. The entire resulting codeword is stored in a storage medium. At least n′| 01-27-2011 | |
| 20110029754 | MULTI-BIT-PER-CELL FLASH MEMORY DEVICE WITH NON-BIJECTIVE MAPPING - To store a plurality of input bits, the bits are mapped to a corresponding programmed state of one or more memory cells and the cell(s) is/are programmed to that corresponding programmed state. The mapping may be many-to-one or may be an “into” generalized Gray mapping. The cell(s) is/are read to provide a read state value that is transformed into a plurality of output bits, for example by maximum likelihood decoding or by mapping the read state value into a plurality of soft bits and then decoding the soft bits. | 02-03-2011 |
| 20110063918 | IDENTIFYING AT-RISK DATA IN NON-VOLATILE STORAGE - The non-volatile storage system predicts which blocks (or other units of storage) will become bad based on performance data. User data in those blocks predicted to become bad can be re-programmed to other blocks, and the blocks predicted to become bad can be removed from further use. | 03-17-2011 |
| 20110066902 | SYSTEM AND METHOD OF READING DATA USING A RELIABILITY MEASURE - In a particular embodiment, a data storage device includes a memory array including a target memory cell and one or more other memory cells. The data storage device also includes a controller coupled to the memory array. The controller is configured to directly compute a reliability measure for at least one bit stored in the target memory cell of the memory array based on a voltage value associated with the target memory cell and based on one or more corresponding voltage values associated with each of the one or more other memory cells of the memory array. | 03-17-2011 |
| 20110093652 | MULTI-BIT-PER-CELL FLASH MEMORY DEVICE WITH NON-BIJECTIVE MAPPING - To store input data in a plurality of memory cells, a mapping function of bit sequences to physical parameter states of the cells is provided. The cells are programmed, in accordance with the mapping function, to store the input data, in a way that would store uniformly distributed data with a programming state distribution other than any native state distribution of the mapping function. To store input data in a single memory cell, a mapping function of bit sequences to states of a physical parameter of the cell, such that if uniformly distributed data were stored in a plurality of such memory cells then the states of the physical parameter of the cells would be distributed non-uniformly, is provided. The memory cell is programmed to store the input data in accordance with the mapping function. | 04-21-2011 |
| 20110134692 | ADAPTIVE DYNAMIC READING OF FLASH MEMORIES - A data storage device includes a controller and storage elements. The controller is configured to read a threshold voltage of each of a plurality of the storage elements to generate read threshold data and to assign reference voltages defining each of a plurality of voltage threshold states based on the read threshold data. | 06-09-2011 |
| 20110157981 | FLASH MEMORY SYSTEM HAVING CROSS-COUPLING COMPENSATION DURING READ OPERATION - A method for reading an addressed cell of a memory system comprises applying at least two different voltage levels to a control gate of a memory cell in an array of memory cells, wherein the memory cell is adjacent to and in electrical field communication with the addressed memory cell. A threshold voltage of the addressed memory cell is measured at each of the at least two different applied voltage levels. At least two of the measured threshold voltages of the addressed memory cell are converted to one or more bit values stored in the addressed memory cell. The bit values are provided to a host of the memory system. An apparatus implementing the method is also disclosed. | 06-30-2011 |
