Abstract: Exemplary embodiments provide wear spreading among die regions (i.e., one or more circuits) in an integrated circuit or among dies by using operating condition data in addition to or instead of environmental data such as temperature data, from each of a plurality of die regions. Control logic produces a cumulative amount of time each of the plurality of die regions has spent at an operating condition based on operating condition data wherein the operating condition data is based on at least one of the following operating characteristics: frequency of operation of the plurality of die regions, an operating voltage of the plurality of die regions, an activity level of the plurality of die regions, a timing margin of the plurality of die regions, and a number of detected faults of the plurality of die regions. The method and apparatus spreads wear among the plurality of same type of die regions by controlling task execution among the plurality of die regions using the die wear-out data.

Abstract: Provided is a memory device including a memory structure including a substrate, a channel region, first and second doped regions, a floating gate and a dielectric layer. The channel region is disposed on the substrate. The first and the second doped regions are disposed on the substrate and respectively located at two sides of the channel region. The floating gate is disposed on the channel region. The dielectric layer is disposed between the floating gate and the channel region, the first doped region and the second doped region. The floating gate and the first doped region are partially overlapped, and/or the floating gate and the second doped region are not overlapped and a sidewall of the floating gate adjacent to the second doped region and a boundary between the second doped region and the channel region are separated by a distance.

Abstract: Exemplary embodiments provide thermal wear spreading among a plurality of thermal die regions in an integrated circuit or among dies by using die region wear-out data that represents a cumulative amount of time each of a number of thermal die regions in one or more dies has spent at a particular temperature level. In one example, die region wear-out data is stored in persistent memory and is accrued over a life of each respective thermal region so that a long term monitoring of temperature levels in the various die regions is used to spread thermal wear among the thermal die regions. In one example, spreading thermal wear is done by controlling task execution such as thread execution among one or more processing cores, dies and/or data access operations for a memory.

Abstract: A NOR string includes a number of individually addressable thin-film storage transistors sharing a bit line, with the individually addressable thin-film transistors further grouped into a predetermined number of segments. In each segment, the thin-film storage transistors of the segment share a source line segment, which is electrically isolated from other source line segments in the other segments within the NOR string. The NOR string may be formed along an active strip of semiconductor layers provided above and parallel a surface of a semiconductor substrate, with each active strip including first and second semiconductor sublayers of a first conductivity and a third semiconductor sublayer of a second conductivity, wherein the shared bit line and each source line segment are formed in the first and second semiconductor sublayers, respectively.

Abstract: An example method includes, performing a first erase verify on a first set of memory cells of a portion of an array of memory cells, performing a second erase verify on a second set of memory cells of the portion of the array, applying a first erase voltage pulse concurrently to each memory cell in the portion of the array if the first set fails the first erase verify and if the second set fails the second erase verify, and applying a second erase voltage pulse concurrently to each memory cell in the portion of the array if the first set passes the first erase verify and if the second set fails the second erase verify. The second erase voltage pulse is different than the first erase voltage pulse.

Abstract: A memory system may include a memory cell array including a plurality of memory blocks; a peripheral circuit configured to apply a check voltage for acquiring check data to a target memory block and apply program voltages to the target memory block in a pre-program operation for the target memory block; and a controller configured to control the peripheral circuit, determine status information on the target memory block based on the check data, and variably apply a program start voltage to the target memory block based on the status information in the pre-program operation.

Abstract: According to one embodiment, a semiconductor memory device includes: a memory cell array including a first memory cell, a first word line, a first circuit coupled to the first word line, a first driver used for a write operation and a read operation, a second driver used for an erase operation, and a voltage generator. The first circuit includes: a second circuit capable of electrically coupling the first word line and a first interconnect; a third circuit capable of electrically coupling the first interconnect and a second interconnect; a fourth circuit capable of electrically coupling the second interconnect and the first driver in the write and read operations; and a fifth circuit capable of electrically coupling the second interconnect and the second driver in the erase operation.

Abstract: A hardware model of a memory comprises: first circuitry configured to supply a memory status value for the memory which is changed upon a full-memory erase operation; second circuitry configured to supply a sector status value for each memory sector of the memory which is changed to a value equal to the memory status value when a write operation is performed on the each memory sector of the memory; and third circuitry configured to supply, when a read operation is performed on a memory sector of the memory, a value stored in the memory sector as output of the read operation if the sector status value for the memory sector is equal to the memory status value or a predefined value as the output of the read operation in other situations.

Abstract: In an embodiment, a method is provided for controlling a level of a read current in a non-volatile memory that is powered by a supply voltage includes. A model current representative of an actual current able to flow during a readout through a read path of the memory is determined based on the value of the supply voltage. The model current is compared to a reference current having a reference value. A control signal is generated. The control signal is to control the generation of the read current having a level equal to the lowest value between a fraction of the value of the model current and the reference value.

Abstract: A semiconductor memory device includes a memory cell array, a read/write circuit and a control logic. The memory cell array includes a plurality of memory cells. The read/write circuit is configured to write data to the memory cell array or read data from the memory cell array. The control logic is configured to control the read/write circuit to perform a read/write operation for the memory cell array. The memory cell array includes a plurality of memory blocks, and each of the memory blocks includes a plurality of sub-blocks. During an operation of erasing a sub-block in a memory block, the control logic selects a sub-block to be erased regardless of a sequence in which the sub-blocks have been programmed, and determines an erase verify voltage based on a position of the selected sub-block.

Abstract: The memory system, may include: a memory device comprising a plurality of memory blocks; and a controller suitable for performing a command operation to the memory blocks, updating update parameters and erase cycles (ECs) of the memory blocks, selecting at least one source memory block based on the update parameters, selecting at least one target memory block based on the ECs, and performing at least one swap operation between the selected at least one or more source memory block and the selected at least one target memory block.

Abstract: A method of monitoring memory performance comprises selecting a first portion of memory from two or more portions of memory in accordance with an adaptive mode indicated by configuration bits in a control register; monitoring memory accesses to the selected portion of memory during a first sampling period; selecting a different portion of memory from the two or more portions of memory in accordance with the adaptive mode for monitoring the different portion of memory in a subsequent sampling period; monitoring memory accesses to the different portion of memory during the subsequent sampling period; recording a respective number of memory accesses for each portion of memory over a plurality of sampling periods; and generating one or more interrupts to output data regarding the monitored memory accesses for data analysis.

Abstract: A brownout tolerant EEPROM emulator (18) manages memory operations at a volatile memory (20) and non-volatile memory (24) using a plurality of sector status bits (451) and forward/reverse skip flags (452, 453) stored in a sector identification record (45) of each sector to define a plurality of status indicators arranged sequentially to specify a plurality of sector configuration states for each memory sector, and to automatically bypass one or more dead sectors in the non-volatile memory array during forward copydown and reverse search operations.

Abstract: A storage control device includes a processor. The processor is configured to request a plurality of disk devices storing data therein to notify the processor of degradation information on degradation of data stored in the respective disk devices. The processor is configured to instruct, based on first information among notified degradation information, the plurality of disk devices to rewrite data. The first information serves as a trigger of rewriting data. The first information is notified by at least one of the plurality of disk devices.

Abstract: A method to improve accuracy of a low voltage state in flash memory cells and the memory therewith is proposed. In the method, at least one memory cell is selected from among a plurality of memory cells in the non-volatile memory according to a first voltage and a second voltage. The first voltage is less than the second voltage and greater than or equal to an erase state voltage level of the flash memory, and the second voltage is less than or equal to a read voltage level of the flash memory. A recovery erase operation is applied to the at least one selected memory cell, thereby erasing electrical charges of the at least one selected memory cell to lower a threshold voltage of the at least one selected memory cell.

Abstract: An Ultra-low power programming method for N-channel semiconductor Non-Volatile Memory (NVM) is disclosed. In contrast to the grounded voltage at the source electrode of an N-channel semiconductor NVM for the conventional Channel Hot Electron Injection (CHEI) programming, the source electrode in the programming method of the invention is necessarily floating with no voltage bias to prevent applied electrical fields toward the source electrode. The drain electrode of the N-channel semiconductor NVM is reversely biased with a positive voltage VDB relative to the substrate to facilitate the valence band electrons in the P-type substrate to tunnel to the conducting band of the N-type drain electrode. A positive high gate voltage pulse is then applied to the gate electrode of the N-channel semiconductor NVM to collect the surface energetic electrons toward the charge storage material.

Abstract: A method includes, at a non-volatile memory having a three dimensional (3D) memory configuration, performing an erase operation. Performing the erase operation includes providing a first control signal to isolate a first portion of a string of the non-volatile memory from a second portion of the string. Performing the erase operation further includes providing a first erase signal to erase the second portion of the string while data is maintained at the first portion of the string.

Abstract: A nonvolatile memory array is divided into multiple memory groups. The nonvolatile memory array receives an erase command to erase a first set of the memory groups, and not a second set of the memory groups. The control circuitry is responsive to the erase command to erase the first set of memory groups, by applying a recovery bias arrangement that adjusts threshold voltages of memory cells in at least one memory group of the second set of memory groups. By applying the recovery bias arrangement to memory cells in at least one memory group of the second set of memory groups, erase disturb is corrected during the recovery bias arrangement, at least in part.

Abstract: A control circuit executes an erase operation that includes an erase pulse application operation and an erase verify operation. The erase pulse application operation applies an erase pulse voltage to a memory cell to change the memory cell from a write state to an erase state. The erase verify operation applies an erase verify voltage to the memory cell to judge whether the memory cell is in the erase state or not. The control circuit changes conditions of execution of the erase verify operation when the number of times of executions of the erase pulse application operation in one erase operation reaches a first number.

Abstract: Methods and systems are disclosed for dynamic healing of non-volatile memory (NVM) cells within NVM systems. The dynamic healing embodiments described herein relax damage within tunnel dielectric layers for NVM cells that occurs over time from charges (e.g., holes and/or electrons) becoming trapped within these tunnel dielectric layers. NVM operations with respect to which dynamic healing processes can be applied include, for example, erase operations, program operations, and read operations. For example, dynamic healing can be applied where performance for the NVM system degrades beyond a selected performance level for an NVM operation, such as elevated erase/program pulse counts for erase/program operations and bit errors for read operations. A variety of healing techniques can be applied, such as drain stress processes, gate stress processes, and/or other desired healing techniques.

Abstract: A semiconductor device comprises an array of memory cells. Each of the memory cells includes a tunnel dielectric, a well region including a first current electrode and a second current electrode, and a control gate. The first and second current electrodes are adjacent one side of the tunnel dielectric and the control gate is adjacent another side of the tunnel dielectric. A controller is coupled to the memory cells. The controller includes logic to determine when to perform a healing process in the tunnel dielectric of the memory cells, and to apply a first voltage to the first current electrode of the memory cells during the healing process to remove trapped electrons and holes from the tunnel dielectric.

Abstract: An error correcting method of a memory controller which controls a nonvolatile memory device includes judging whether first read data read from the nonvolatile memory device is correctable; reading second read data from the nonvolatile memory device when the first read data is uncorrectable; and correcting an error of the first read data based on error information of the second read data and error information of the first read data.

Abstract: An erase operation for a 3D stacked memory device selectively inhibits subsets of memory cells which meet a verify condition as the erase operation progresses. As a result, the faster-erasing memory cells are less likely to be over-erased and degradation is reduced. Each subset of memory cells can be independently erased by controlling a select gate, drain (SGD) transistor line, a bit line or a word line, according to the type of subset. For a SGD line subset or a bit line subset, the SGD line or bit line, respectively, is set at a level which inhibits erase. For a word line subset, the word line voltage is floated to inhibit erase. An inhibit or uninhibit status can be maintained for each subset, and each type of subset can have a different maximum allowable number of fail bits.

Abstract: A control circuit is configured to execute an erasing operation on a selected cell unit in a selected memory block. In the erasing operation, the control circuit raises the voltage of the bodies of the first memory transistors included in the selected cell unit to a first voltage, sets the voltage of the bodies of the first memory transistors included in the non-selected cell unit to a second voltage lower than the first voltage, and applies a third voltage equal to or lower than the second voltage to the gates of the first memory transistors included in the selected cell unit and the non-selected cell unit.

Abstract: A nonvolatile memory array has a multiple erase procedures of different durations. A block of memory cells of the array can be erased by one of the different erase procedures.

Abstract: An erase operation for a 3D stacked memory device selectively inhibits subsets of memory cells which meet a verify condition as the erase operation progresses. As a result, the faster-erasing memory cells are less likely to be over-erased and degradation is reduced. Each subset of memory cells can be independently erased by controlling a select gate, drain (SGD) transistor line, a bit line or a word line, according to the type of subset. For a SGD line subset or a bit line subset, the SGD line or bit line, respectively, is set at a level which inhibits erase. For a word line subset, the word line voltage is floated to inhibit erase. An inhibit or uninhibit status can be maintained for each subset, and each type of subset can have a different maximum allowable number of fail bits.

Abstract: A non-volatile semiconductor memory device according to one embodiment of the present invention includes a memory cell array and a control unit. The control unit is configured to control a repeat of an erase operation, an erase verify operation, and a step-up operation. The control unit is configured to perform a soft-programming operation of setting the memory cells from an over-erased state to a first threshold voltage distribution state when, in a series of erase operations, the number of erase voltage applications is more than a first number and less than a second number (the first number<the second number). The control unit is configured not to perform the soft-programming operation when the number of erase voltage applications is equal to or less than the first number or equal to or more than the second number.

Abstract: A block dividing unit groups one-word lines into p groups, to divide a block into p divisional blocks. An erasing unit has an erasing operation performed on data stored in memory cells in a memory cell array, on a divisional block basis. An erasing verifying unit has an erasing verifying operation performed on memory cells subjected to the erasing operation, on a divisional block basis.

Abstract: A non-volatile storage system performs programming for a plurality of non-volatile storage elements and selectively performs re-erasing of at least a subset of the non-volatile storage elements that were supposed to remain erased, without intentionally erasing programmed data.

Abstract: Techniques are described herein for detecting and recovering over-erased memory cells in a flash memory device. In one embodiment, a flash memory device includes a memory array including a plurality of blocks of memory cells. The device also includes a command interface to receive a command from a source external to the memory device. The device also includes a controller including logic to perform a leakage-suppression process in response to the command. The leakage-suppression process includes performing a soft program operation to increase a threshold voltage of one or more over-erased memory cells in a given block of memory cells and establish an erased state.

Abstract: A computer-implemented method of managing a memory of a non-volatile solid state memory device by balancing write/erase cycles among blocks to level block usage. The method includes monitoring an occurrence of an error during a read operation in a memory unit of the device, where the error is correctable by error-correcting code, and programming the memory unit according to the monitored occurrence of the error, where the step of monitoring the occurrence of an error is carried out for at least one block, and wherein said step of programming includes wear-leveling the monitored block according the error monitored for the monitored block.

Abstract: An erase operation of a memory apparatus is controlled by, inter alia, selecting one or more memory cell blocks to be erased among a plurality of memory cell blocks, performing an erase operation on the selected one or more memory cell blocks in response to an erase command, performing a first soft program operation on the selected one or more memory cell blocks if the erase operation is determined as passed, and performing a second soft program operation on the selected one or more memory cell blocks if the first soft program operation is determined as passed.

Abstract: A method of decreasing the test time to determine data retention (e.g. leakage current) of a memory cell having a floating gate for the storage of charges thereon. The memory cell is characterized by the leakage current having a rate of leakage which is dependent upon the absolute value of the voltage of the floating gate. The memory cell is further characterized by a first erase voltage and a first programming voltage, applied during normal operation, and a first read current detected during normal operation. The method applies a voltage greater than the first erase voltage or greater than the first programming voltage, to over erase the floating gate. The memory cell including the floating gate is subject to a single high temperature bake. The memory cell is then tested for data retention of the floating gate based on the single high temperature bake.

Abstract: Embodiments of the present disclosure provide methods, devices, modules, and systems for healing non-volatile memory cells. One method includes biasing a first select gate transistor coupled to a string of memory cells at a first voltage, biasing a second select gate transistor coupled to the string at a second voltage, applying a first healing voltage to a first edge word line in order to extract charge accumulated between the first select gate transistor and a first edge memory cell stack of the string, and applying a second healing voltage to a second edge word line in order to extract charge accumulated between the second select gate transistor and a second edge memory cell stack of the string.

Abstract: A control circuit is configured to execute an erasing operation on a selected cell unit in a selected memory block. In the erasing operation, the control circuit raises the voltage of the bodies of the first memory transistors included in the selected cell unit to a first voltage, sets the voltage of the bodies of the first memory transistors included in the non-selected cell unit to a second voltage lower than the first voltage, and applies a third voltage equal to or lower than the second voltage to the gates of the first memory transistors included in the selected cell unit and the non-selected cell unit.

Abstract: A vertical NAND structure includes one or more mid-string devices having at least two functional modes. In the first mode, the one or more mid-string devices couple the bodies of stacks of NAND memory cells to the substrate for erase operations. In the second mode, the one or more mid-string devices couple the body of a first stack of NAND memory cells to a body of a second stack of memory NAND memory cells, allowing the two stacks operate as a single NAND string for read and programming operations.

Abstract: A NAND flash memory device and method of erasing memory cells thereof, wherein each cell is only subjected to the level of erase voltage needed to restore its nominal “erased” state. Each memory cell of the NAND flash memory device comprises a floating gate, a control gate connected to a wordline and receives a control voltage therefrom to induce a programming charge on the floating gate, and a bitline adapted to apply an erase voltage to deplete the floating gate of the programming charge. Each memory cell further includes circuitry for modulating the erase voltage according to the level of the programming charge on its floating gate.

Abstract: Various aspects of a nonvolatile memory have an improved erase suspend procedure. A bias arrangement is applied to word lines of an erase sector undergoing an erase procedure interrupted by an erase suspend procedure. As a result, another operation performed during erase suspend, such as a read operation or program operation, has more accurate results due to decreased leakage current from any over-erased nonvolatile memory cells of the erase sector.

Abstract: A memory cartridge is described that includes a non-volatile memory. The cartridge also includes logic to concentrate memory operations on particular areas of the non-volatile memory to cause the areas of concentration to wear out at an accelerated rate relative to non areas of concentration, and logic to track wear on the non-volatile memory resulting from one or both of erases and writes.

Abstract: A non-volatile semiconductor memory device according to one embodiment of the present invention includes a memory cell array and a control unit. The control unit is configured to control a repeat of an erase operation, an erase verify operation, and a step-up operation. The control unit is configured to perform a soft-programming operation of setting the memory cells from an over-erased state to a first threshold voltage distribution state when, in a series of erase operations, the number of erase voltage applications is more than a first number and less than a second number (the first number<the second number). The control unit is configured not to perform the soft-programming operation when the number of erase voltage applications is equal to or less than the first number or equal to or more than the second number.

Abstract: A controller in a flash memory device manages erase count of each physical block and manages the erase frequency of each logical block. The controller allocates a logical block whose erase frequency is high to one or more physical blocks whose erase count is low.

Abstract: A method of decreasing the test time to determine data retention (e.g. leakage current) of a memory cell having a floating gate for the storage of charges thereon. The memory cell is characterized by the leakage current having a rate of leakage which is dependent upon the absolute value of the voltage of the floating gate. The memory cell is further characterized by a first erase voltage and a first programming voltage, applied during normal operation, and a first read current detected during normal operation. The method applies a voltage greater than the first erase voltage or greater than the first programming voltage, to over erase the floating gate. The memory cell including the floating gate is subject to a single high temperature bake. The memory cell is then tested for data retention of the floating gate based on the single high temperature bake.

Abstract: Methods of erasing a memory, methods of operating a memory, memory devices, and systems. In one such method, an erase block is erased to an intermediate erase voltage before it is erased to a final erase voltage, such as to tighten an erase distribution. Faster erasing cells have their erasing throttled using a positive bias on their access line once a particular number of cells coupled to the access line are erased to the intermediate erase voltage.

Abstract: A computer-implemented method of managing a memory of a non-volatile solid state memory device by balancing write/erase cycles among blocks to level block usage. The method includes: monitoring an occurrence of an error during a read operation in a memory unit of the device, wherein the error is correctable by error-correcting code; and programming the memory unit according to the monitored occurrence of the error; wherein the step of monitoring the occurrence of an error is carried out for at least one block; and wherein said step of programming comprises wear-leveling the monitored block according the error monitored for the monitored block. A computer system and a computer program-product is also provided. The non-volatile solid state memory device includes: a memory unit having data stored therein; and a controller with a logic for programming the memory unit according to a monitored occurrence of an error during a read operation.

Abstract: A method includes erasing bits and identifying bits that have been over-erased by the erasing. A first subset of the bits that have been over-erased are soft programmed. The results of soft programming the first subset of bits is measured. An initial voltage condition from a plurality of possible voltage conditions based on the results from soft programming the first subset of bits is selected. A second subset of bits that have been over-erased are soft programmed. The soft programming applies the initial voltage condition to the bits in the second subset of bits. The second subset comprises bits that are still over-erased when the step of selecting occurs. The result is that the soft programming for the second subset may begin at a more optimum point for quickly achieving the needed soft programming to bring all of the bits within the desired erase condition.

Abstract: According to one embodiment, a method is disclosed for operating a semiconductor memory device. The semiconductor memory device includes a substrate, a stacked body, a memory film, a channel body, a select transistor, and a wiring. The method can boost a potential of the channel body by applying a first erase potential to the wiring, the select gate, and the word electrode layer. In addition, after the boosting of the potential of the channel body, with the wiring and the select gate maintained at the first erase potential, the method can decrease a potential of the word electrode layer to a second erase potential lower than the first erase potential.

Abstract: A method of erasing a memory block of a non-volatile memory, including setting a pulse width of erase pulses to an initial width, repeatedly applying erase pulses to the memory block until the memory block meets an erase metric or until a maximum number of erase pulses have been applied, gradually adjusting a pulse voltage magnitude of the erase pulses from an initial pulse voltage level to a maximum pulse voltage level, and reducing the width of the erase pulses to less than the initial width when the pulse voltage magnitude reaches an intermediate voltage level between the initial pulse voltage level and the maximum pulse voltage level. Thus, narrow pulses are applied at higher voltage levels to reduce the amount of over erasure of the memory block.

Abstract: A system and a method for reprogramming a non volatile memory (NVM) portion, the method includes: receiving an initial content of an NVM portion; wherein the initial content differs from an erase content of the NVM portion; processing the previously programmed content in response to input content that should be represented by an initial content of the NVM portion; wherein the processing is characterized by a write limitation that prevents a non-erase value of a bit to be changed to an erase value; wherein the processing comprises at least one out of skip value based encoding, generating error correction information and error correction code based encoding; and writing the processed content of the NVM portion to the NVM portion.

Abstract: A method for erasing a flash EEPROM memory device is disclosed. The memory device has a first semiconductor region of one conductivity type formed within a second semiconductor region of an opposite conductivity type, source and drain regions formed from a semiconductor layer of the opposite conductivity type in the first semiconductor region, a well electrode formed from a semiconductor layer of the conductivity type inside the first semiconductor region, a charge storing layer electrically isolated from the first semiconductor region by a dielectric layer and having electric charge retention properties, and a control gate electrode electrically isolated from the charge storing layer by a inter layer of coupling dielectrics.

Abstract: A non-volatile semiconductor memory is disclosed comprising a memory device including a plurality of memory segments. A program command is issued to the memory device to program a memory segment, and a program time required to execute the program command is saved. An erase command is issued to the memory device to erase the memory segment, and an erase time required to execute the erase command is saved. A wear leveling algorithm is executed for the memory segment in response to the program time and the erase time.