Abstract: A method for data storage includes storing data in a target analog memory cell, which is one of a group of analog memory cells that are connected in series with one another, by writing an input storage value into the target memory cell. A first read operation, which reads a first output storage value from the target memory cell while biasing the other memory cells with respective first pass voltages, is applied to the target memory cell. A second read operation, which reads a second output storage value from the target memory cell while biasing the other memory cells with respective second pass voltages, is applied to the target memory cell. At least one of the second pass voltages is different from a respective first pass voltage. The data is reconstructed responsively to the first and second output storage values.

Abstract: A method for operating a memory (28) includes storing data, which is encoded with an Error Correction Code (ECC), in analog memory cells (32) of the memory by writing respective analog input values selected from a set of nominal values to the analog memory cells. The stored data is read by performing multiple read operations that compare analog output values of the analog memory cells to different, respective read thresholds so as to produce multiple comparison results for each of the analog memory cells. At least two of the read thresholds are positioned between a pair of the nominal values that are adjacent to one another in the set of the nominal values. Soft metrics are computed responsively to the multiple comparison results. The ECC is decoded using the soft metrics, so as to extract the data stored in the analog memory cells.

Abstract: A method for data storage in analog memory cells includes defining multiple programming states for storing data in the analog memory cells. The programming states represent respective combinations of more than one bit and correspond to respective, different levels of a physical quantity stored in the memory cells. The data is stored in the memory cells by applying to the memory cells programming pulses that cause the levels of the physical quantity stored in the memory cells to transition between the programming states, such that a given transition is caused by only a single programming pulse.

Abstract: A method for storage includes collecting information regarding respective performance characteristics of a plurality of memory units in a memory array, each memory unit including one or more cells of the memory array. When data are received for storage in the memory array, a memory unit is selected responsively to the respective performance characteristics, and the received data are stored in the selected memory unit.

Abstract: A method for storing data in a memory, which includes a plurality of analog memory cells, includes defining programming levels that represent respective combinations of at least first and second bits and are represented by respective nominal storage values. The data is stored by mapping the data to storage values selected from among the nominal storage values and writing the storage values to the memory cells. A condition is defined over two or more bit-specific error rates applicable respectively to at least the first and second bits. The bit-specific error rates include a first bit-specific error rate computed over the data stored by the first bits and a second bit-specific error rate computed, separately from the first bit-specific error rate, over the data stored by the second bits. The nominal storage values are set based on the bit-specific error rates so as to meet the condition.

Abstract: A method for data storage includes storing first data in analog memory cells using a first programming operation, which writes to the memory cells respective analog values representing respective bit values of the first data. Second data is stored in the analog memory cells in addition to the first data using a second programming operation, which modifies the respective analog values of the memory cells so as to represent bit value combinations of the first and second data. The first and second programming operations are defined such that, at all times during the second programming operation, the analog value of each memory cell remains unambiguously indicative of the respective bit value of the first data stored in that memory cell.

Abstract: A method for operating a memory that includes a plurality of analog memory cells includes storing data in a first group of the memory cells by writing respective first cell values to the memory cells in the first group. After storing the data, respective second cell values are read from the memory cells in the first group, and differences are found between the respective first and second cell values for each of one or more of the memory cells in the first group. The differences are processed to produce error information, and the error information is stored in a second group of the memory cells.

Abstract: A method for data storage in a memory that includes a plurality of analog memory cells includes storing data in the memory by writing first storage values to the cells. One or more read reference levels are defined for reading the cells, such that at least one of the read reference levels is negative. After storing the data, second storage values are read from the cells using the read reference levels, so as to reconstruct the stored data. In another disclosed method, data is stored in the memory by mapping the data to first storage values selected from a set of the nominal storage values, and writing the first storage values to the cells. The set of nominal storage values is defined such that at least one of the nominal storage values is negative.

Abstract: A method includes defining a nominal level of a physical quantity to be stored in analog memory cells for representing a given data value. The given data value is written to the cells in first and second groups of the cells, which have respective first and second programming responsiveness such that the second responsiveness is different from the first responsiveness, by applying to the cells in the first and second groups respective, different first and second patterns of programming pulses that are selected so as to cause the cells in the first and second groups to store respective levels of the physical quantity that fall respectively in first and second ranges, such that the first range is higher than and the second range is lower than the nominal level. The given data value is read from the cells at a later time.

Abstract: A method for decoding an Error Correction Code (ECC) includes accepting coefficients, including at least first and second coefficients, of an Error Locator Polynomial (ELP) that is defined over a vector space and has at least one root that is indicative of a location of an error in a set of bits, which represent data that has been encoded with the ECC. The first coefficient is represented using a first basis of the vector space, and the second coefficient is represented using a second basis of the vector space, different from the first basis. Using processing circuitry, the root of the ELP is identified by applying algebraic operations to the coefficients, such that the algebraic operations are applied to the first coefficient using the first basis, and to the second coefficient using the second basis. The error is corrected responsively to the identified root of the ELP.

Abstract: A method for operating a memory (20) includes storing analog values in an array of analog memory cells (22), so that each of the analog memory cells holds an analog value corresponding to at least first and second respective bits. A first indication of the analog value stored in a given analog memory cell is obtained using a first set of sampling parameters. A second indication of the analog value stored in the given analog memory cell is obtained using a second set of sampling parameters, which is dependent upon the first indication. The first and second respective bits are read out from the given analog memory cell responsively to the first and second indications.

Abstract: A method for data storage includes, in a system that includes a host having a host memory and a memory controller that is separate from the host and stores data for the host in a non-volatile memory including multiple analog memory cells, storing in the host memory information items relating to respective groups of the analog memory cells of the non-volatile memory. A command that causes the memory controller to access a given group of the analog memory cells is received from the host. In response to the command, a respective information item relating to the given group of the analog memory cells is retrieved from the host memory by the memory controller, and the given group of the analog memory cells is accessed using the retrieved information item.

Abstract: A method includes accepting a definition of a type of multi-unit memory device (28) including a set of memory units (24), each having a respective nominal storage capacity, the definition specifying a target memory size of the memory device such that a sum of nominal storage capacities of the memory units in the set is equal to the target memory size. A plurality of the memory units is accepted. The memory units have respective actual storage capacities, at least some of which differ from the respective nominal storage capacity. Multi-unit memory devices including respective sets of the memory units are assembled, such that at least one of the sets includes at least a first memory unit having a first actual capacity that is less than the respective nominal capacity and at least a second memory unit having a second actual capacity that is greater than the nominal capacity.

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 programming a first group of analog memory cells at a first time at a known first temperature, so as to cause the analog memory cells in the first group to assume respective first analog storage values. Respective second analog storage values are read from the analog memory cells in the first group at a second time at which the analog memory cells are at a second temperature. A shift is estimated between the first analog storage values and the second analog storage values, and a memory access parameter is adjusted responsively to the estimated shift. A second group of the analog memory cells is accessed at the second temperature using the adjusted memory access parameter.

Abstract: A method for data storage in a memory that includes a plurality of analog memory cells includes storing data in the memory by writing first storage values to the cells. One or more read reference levels are defined for reading the cells, such that at least one of the read reference levels is negative. After storing the data, second storage values are read from the cells using the read reference levels, so as to reconstruct the stored data. In another disclosed method, data is stored in the memory by mapping the data to first storage values selected from a set of the nominal storage values, and writing the first storage values to the cells. The set of nominal storage values is defined such that at least one of the nominal storage values is negative.

Abstract: A method for data storage includes performing an erasure operation on a group of analog memory cells (32). One or more of the memory cells in the group, which failed the erasure operation, are identified as erase-failed cells. A storage configuration that is used for programming the analog memory cells in the group is modified responsively to the identified erase-failed cells. Data is stored in the group of the analog memory cells using the modified storage configuration.

Abstract: A method for data storage in a memory that includes a plurality of analog memory cells includes storing data in the memory by writing first storage values to the cells. One or more read reference levels are defined for reading the cells, such that at least one of the read reference levels is negative. After storing the data, second storage values are read from the cells using the read reference levels, so as to reconstruct the stored data. In another disclosed method, data is stored in the memory by mapping the data to first storage values selected from a set of the nominal storage values, and writing the first storage values to the cells. The set of nominal storage values is defined such that at least one of the nominal storage values is negative.

Abstract: A method for data storage in a memory that includes multiple analog memory cells fabricated using respective physical media, includes identifying a group of the memory cells whose physical media have deteriorated over time below a given storage quality level. A rejuvenation process, which causes the physical media of the memory cells in the group to meet the given storage quality level, is applied to the identified group. Data is stored in the rejuvenated group of the memory cells.

Abstract: A method for operating a memory (28) includes storing data, which is encoded with an Error Correction Code (ECC), in analog memory cells (32) of the memory by writing respective analog input values selected from a set of nominal values to the analog memory cells. The stored data is read by performing multiple read operations that compare analog output values of the analog memory cells to different, respective read thresholds so as to produce multiple comparison results for each of the analog memory cells. At least two of the read thresholds are positioned between a pair of the nominal values that are adjacent to one another in the set of the nominal values. Soft metrics are computed responsively to the multiple comparison results. The ECC is decoded using the soft metrics, so as to extract the data stored in the analog memory cells.