Abstract: A method for data storage includes storing data in a group of memory cells, by encoding the data using at least an outer code and an inner code, and optionally inverting the encoded data prior to storing the encoded data in the memory cells. The encoded data is read from the memory cells, and inner code decoding is applied to the read encoded data to produce a decoding result. At least part of the read data is conditionally inverted, depending on the decoding result of the inner code.

Abstract: A method in a non-volatile memory, which includes multiple memory cells that store data using a predefined set of programming levels including an erased level, includes receiving a storage operation indicating a group of the memory cells that are to be retained without programming for a long time period. The memory cells in the group are set to a retention programming level that is different from the erased level. Upon preparing to program the group of memory cells with data, the group of memory cells is erased to the erased level and the data is then programmed in the group of memory cells.

Abstract: A method for data storage includes defining a first programming scheme that programs a group of analog memory cells while reducing interference caused by at least one memory cell that neighbors the group, and a second programming scheme that programs the group of the analog memory cells and does not reduce all of the interference reduced by the first programming scheme. One of the first and second programming schemes is selected based on a criterion defined with respect to the analog memory cells. Data is stored in the group of the analog memory cells using the selected programming scheme.

Abstract: A method for data storage includes, in a first programming phase, storing first data in a group of memory cells by programming the memory cells in the group to a set of initial programming levels. In a subsequent second programming phase, second data is stored in the group by identifying the memory cells in the group that were programmed in the first programming phase to respective levels in a predefined partial subset of the initial programming levels, and programming only the identified memory cells with the second data, so as to set at least some of the identified memory cells to one or more additional programming levels that are different from the initial programming levels. The memory cells to which the second data was programmed are recognized by reading only a partial subset of the first data. The second data is read from the recognized memory cells.

Abstract: A method includes, in a plurality of memory cells that share a common isolation layer and store in the common isolation layer quantities of electrical charge representative of data values, assigning a first group of the memory cells for data storage, and assigning a second group of the memory cells for protecting the electrical charge stored in the first group from retention drift. Data is stored in the memory cells of the first group. Protective quantities of the electrical charge that protect from the retention drift in the memory cells of the first group are stored in the memory cells of the second group.

Abstract: Methods for Error Correction Code (ECC) decoding include producing syndromes from a set of bits, which represent data that has been encoded with the ECC. An Error Locator Polynomial (ELP) is generated based on the syndromes. At least some of the ELP roots are identified, and the errors indicated by these roots are corrected. Each syndrome may be produced by applying to the bits vector operations in a vector space. Each syndrome is produced by applying vector operations using a different basis of the vector space. The ELP may be evaluated on a given field element by operating on ELP coefficients using serial multipliers, wherein each serial multiplier performs a sequence of multiplication cycles and produces an interim result in each cycle. Responsively to detecting at least one interim result indicating that the given element is not an ELP root, the multiplication cycles are terminated before completion of the sequence.

Abstract: A method for operating a memory includes storing data in a plurality of analog memory cells that are fabricated on a first semiconductor die by writing input storage values to a group of the analog memory cells. After storing the data, multiple output storage values are read from each of the analog memory cells in the group using respective, different threshold sets of read thresholds, thus providing multiple output sets of the output storage values corresponding respectively to the threshold sets. The multiple output sets of the output storage values are preprocessed by circuitry that is fabricated on the first semiconductor die, to produce preprocessed data. The preprocessed data is provided to a memory controller, which is fabricated on a second semiconductor die that is different from the first semiconductor die. so as to enable the memory controller to reconstruct the data responsively to the preprocessed data.

Abstract: A data storage method includes identifying, in a set of data items associated with respective logical addresses for storage in a memory, a first subset of the logical addresses associated with the data items containing application data, and a second subset of the logical addresses associated with the data items containing parity information that has been calculated over the application data. The data items associated with the first identified subset are stored in one or more first physical memory areas of the memory, and the data items associated with the second identified subset are stored in one or more second physical memory areas of the memory, different from the first physical memory areas. A memory management task is performed independently in the first physical memory areas and in the second physical memory areas.

Abstract: A method for data storage includes storing data in a group of memory cells, by encoding the data using at least an outer code and an inner code, and optionally inverting the encoded data prior to storing the encoded data in the memory cells. The encoded data is read from the memory cells, and inner code decoding is applied to the read encoded data to produce a decoding result. At least part of the read data is conditionally inverted, depending on the decoding result of the inner code.

Abstract: A method for data storage includes defining, in a memory that includes multiple analog memory cells, an erased state, a set of non-erased programming states and a partial subset of the non-erased programming states. Data is initially stored in a first group of the analog memory cells by programming each of at least some of the memory cells in the first group from the erased state to a respective non-erased programming state selected from the set of non-erased programming states. After initially storing the data, a second group of the analog memory cells, which potentially cause interference to the first group, is programmed. After programming the second group, the first group is selectively re-programmed with the data by repeating programming of only the memory cells in the first group whose respective programming states belong to the partial subset.

Abstract: A method includes storing data values in a group of memory cells that share a common isolating layer, by producing quantities of electrical charge representative of the data values at respective regions of the common isolating layer that are associated with the memory cells. A function, which relates a drift of the electrical charge in a given memory cell in the group to the data values stored in one or more other memory cells in the group, is estimated. The drift is compensated for using the estimated function.

Abstract: A method for data storage includes encoding each of multiple data items individually using a first Error Correction Code (ECC) to produce respective encoded data items. The encoded data items are stored in a memory. The multiple data items are encoded jointly using a second ECC, so as to produce a code word of the second ECC, and only a part of the code word is stored in the memory. The stored encoded data items are recalled from the memory and the first ECC is decoded in order to reconstruct the data items. Upon a failure to reconstruct a given data item from a respective given encoded data item by decoding the first ECC, the given data item is reconstructed based on the part of the code word of the second ECC and on the encoded data items other than the given encoded data item.

Abstract: Methods for Error Correction Code (ECC) decoding include producing syndromes from a set of bits, which represent data that has been encoded with the ECC. An Error Locator Polynomial (ELP) is generated based on the syndromes. At least some of the ELP roots are identified, and the errors indicated by these roots are corrected. Each syndrome may be produced by applying to the bits vector operations in a vector space. Each syndrome is produced by applying vector operations using a different basis of the vector space. The ELP may be evaluated on a given field element by operating on ELP coefficients using serial multipliers, wherein each serial multiplier performs a sequence of multiplication cycles and produces an interim result in each cycle. Responsively to detecting at least one interim result indicating that the given element is not an ELP root, the multiplication cycles are terminated before completion of the sequence.

Abstract: A method includes, in a plurality of memory cells that share a common isolation layer and store in the common isolation layer quantities of electrical charge representative of data values, assigning a first group of the memory cells for data storage, and assigning a second group of the memory cells for protecting the electrical charge stored in the first group from retention drift. Data is stored in the memory cells of the first group. Protective quantities of the electrical charge that protect from the retention drift in the memory cells of the first group are stored in the memory cells of the second group.

Abstract: A method for operating a memory includes storing data in a plurality of analog memory cells that are fabricated on a first semiconductor die by writing input storage values to a group of the analog memory cells. After storing the data, multiple output storage values are read from each of the analog memory cells in the group using respective, different threshold sets of read thresholds, thus providing multiple output sets of the output storage values corresponding respectively to the threshold sets. The multiple output sets of the output storage values are preprocessed by circuitry that is fabricated on the first semiconductor die, to produce preprocessed data. The preprocessed data is provided to a memory controller, which is fabricated on a second semiconductor die that is different from the first semiconductor die. so as to enable the memory controller to reconstruct the data responsively to the preprocessed data.

Abstract: A method includes, in a storage system that includes multiple memory devices, holding a definition of a given type of storage command. Multiple storage commands of the given type are executed in the memory devices, such that an actual current consumption of each storage command deviates from a nominal current waveform defined for the given type by no more than a predefined deviation, and such that each storage command is preceded by a random delay.

Abstract: A method for data storage includes storing data in a memory that includes one or more memory units, each memory unit including memory blocks. The stored data is compacted by copying at least a portion of the data from a first memory block to a second memory block, and subsequently erasing the first memory block. Upon detecting a failure in the second memory block after copying the portion of the data and before erasure of the first memory block, the portion of the data is recovered by reading the portion from the first memory block.

Abstract: A method includes accepting a definition of a mother Error Correction Code (ECC) that is represented by a set of parity check equations and includes first code words, and a definition of a punctured ECC that includes second code words and is derived from the mother ECC by removal of one or more of the parity check equations and removal of one or more punctured check symbols selected from among check symbols of the first code words. A mother decoder, which is designed to decode the mother ECC by exchanging messages between symbol nodes and check nodes in accordance with a predefined interconnection scheme that represents the mother ECC, is provided. An input code word of the punctured ECC is decoded using the mother decoder by initializing one or more of the symbol nodes and controlling one or more of the messages, and while retaining the interconnection scheme.

Abstract: A method for data storage includes, in a first programming phase, storing first data in a group of memory cells by programming the memory cells in the group to a set of initial programming levels. In a subsequent second programming phase, second data is stored in the group by identifying the memory cells in the group that were programmed in the first programming phase to respective levels in a predefined partial subset of the initial programming levels, and programming only the identified memory cells with the second data, so as to set at least some of the identified memory cells to one or more additional programming levels that are different from the initial programming levels. The memory cells to which the second data was programmed are recognized by reading only a partial subset of the first data. The second data is read from the recognized memory cells.

Abstract: A method for data storage includes storing data in a group of memory cells, by encoding the data using at least an outer code and an inner code, and optionally inverting the encoded data prior to storing the encoded data in the memory cells. The encoded data is read from the memory cells, and inner code decoding is applied to the read encoded data to produce a decoding result. At least part of the read data is conditionally inverted, depending on the decoding result of the inner code.