Abstract: When a bad block is found in a nonvolatile memory array, the block is marked as a bad block so that it is not subsequently used. The block is also reconfigured as a bad block by increasing resistance of vertical NAND strings in the block by increasing threshold voltage of at least some transistors along vertical NAND strings, for example, select transistors or memory cell transistors.

Abstract: Layers in a multi-layer memory array are categorized according to likely error rates as predicted from their memory hole diameters. Data to be stored along a word line in a high risk layer is subject to a redundancy operation (e.g. XOR) with data to be stored along a word line in a low risk layer so that the risk of both being bad is low.

Abstract: A method may be performed in a data storage device that includes a memory including a three-dimensional (3D) memory and a controller, in response to a request to read data from the memory. The data is located within a first word line of the memory. The method includes accessing the data from the first word line and determining, based on a probability threshold, whether to perform a remedial action with respect to a second word line.

Abstract: When data from a portion of a three dimensional NAND memory array is determined to be uncorrectable by Error Correction Code (ECC), a determination is made as to whether data is uncorrectable by ECC throughout some unit that is larger than the portion. If modified read conditions provide ECC correctable data, the modified read conditions are recorded for subsequent reads of the larger unit.

Abstract: Certain MLC blocks that tend to be reclaimed before they are full may be programmed according to a programming scheme that programs lower pages first and programs upper pages later. This results in more lower page programming than upper page programming on average. Lower page programming is generally significantly faster than upper page programming so that more lower page programming (and less upper programming) reduces average programming time.

Abstract: Portions of data stored in a three dimensional memory array are selected based on their locations for calculation of redundancy data. Locations are selected so that no two portions in a set of portions for a given calculation are likely to become uncorrectable at the same time. Selected portions may be separated by at least one word line and separated by at least one string in a block.

Abstract: In a charge trapping memory, data that would otherwise be likely to remain adjacent to unwritten word lines is written three times, along three immediately adjacent word lines. The middle copy is protected from charge migration on either side and is considered a safe copy for later reading. Dummy data may be programmed along a number of word lines to format a block for good data retention.

Abstract: A method and system for achieving die parallelism through block interleaving includes non-volatile memory having a multiple non-volatile memory dies, where each die has a cache storage area and a main storage area. A controller is configured to receive data and write sequentially addressed data to the cache storage area of a first die. The controller, after writing sequentially addressed data to the cache storage area of the first die equal to a block of the main storage area of the first die, writes additional data to a cache storage area of a next die until sequentially addressed data is written into the cache area of the next die equal to a block of the main storage area. The cache storage area may be copied to the main storage area on the first die while the cache storage area is written to on the next die.

Abstract: A method performed in a data storage device including a non-volatile memory includes reading a representation of data, the representation corresponding to one or more selected states of storage elements of a group of storage elements of the non-volatile memory. The method includes, in response to a count of errors in the representation of the data exceeding a threshold, scheduling a remedial action to be performed on the group of storage elements.

Abstract: Multiple bits of data are programmed together to each cell of a segment of a word line while other segments of the same word line are unprogrammed. Subsequently, additional segments are similarly programmed. Data is read from a partially programmed word line (with a mix of programmed and unprogrammed segments) using a single reading scheme.

Abstract: Multiple bits of data are programmed together to each cell of a segment of a word line while other segments of the same word line are unprogrammed. Subsequently, additional segments are similarly programmed. Data is read from a partially programmed word line (with a mix of programmed and unprogrammed segments) using a single reading scheme.

Abstract: In a Multi Level Cell (MLC) memory array, a burst of data from a host may be written in only lower pages of a block in a rapid manner. Other data from a host may be written in lower and upper pages so that data is more efficiently arranged for long term storage.

Abstract: In a Multi Level Cell (MLC) memory array, a burst of data from a host may be written in only lower pages of a block in a rapid manner. Other data from a host may be written in lower and upper pages so that data is more efficiently arranged for long term storage.

Abstract: In a three-dimensional NAND memory in which a block contains multiple separately-selectable sets of strings connected to the same set of bit lines, sets of strings are zoned, and different operating parameters applied to different zones. Operating parameters for a zone are obtained from characterizing a reference set of strings in the zone.

Abstract: In a charge trapping memory, data that would otherwise be likely to remain adjacent to unwritten word lines is written three times, along three immediately adjacent word lines. The middle copy is protected from charge migration on either side and is considered a safe copy for later reading. Dummy data may be programmed along a number of word lines to format a block for good data retention.

Abstract: Certain MLC blocks that tend to be reclaimed before they are full may be programmed according to a programming scheme that programs lower pages first and programs upper pages later. This results in more lower page programming than upper page programming on average. Lower page programming is generally significantly faster than upper page programming so that more lower page programming (and less upper programming) reduces average programming time.

Abstract: Certain MLC blocks that tend to be reclaimed before they are full may be programmed according to a programming scheme that programs lower pages first and programs upper pages later. This results in more lower page programming than upper page programming on average. Lower page programming is generally significantly faster than upper page programming so that more lower page programming (and less upper programming) reduces average programming time.

Abstract: Certain MLC blocks that tend to be reclaimed before they are full may be programmed according to a programming scheme that programs lower pages first and programs upper pages later. This results in more lower page programming than upper page programming on average. Lower page programming is generally significantly faster than upper page programming so that more lower page programming (and less upper programming) reduces average programming time.

Abstract: In a block-erasable nonvolatile memory array, blocks are categorized as bad blocks, prime blocks, and sub-prime blocks. Sub-prime blocks are identified from their proximity to bad blocks or from testing. Sub-prime blocks are configured for limited operation (e.g. only storing non-critical data, or data copied elsewhere, or using some additional or enhanced redundancy scheme).

Abstract: A number (Nwl) of programmed word lines in a block of NAND strings is determined by measuring a reference combined current (Iref) in the block when all of the memory cells are in a conductive state. Subsequently, to determine if a word line is a programmed word line, an additional combined current (Iadd) in the block is measured with a demarcation voltage applied to the selected word line. The selected word line is determined to be programmed word lines if Idd is less than Iref by at least a margin. Nwl can be used to adjust an erase-verify test of an erase operation by making the erase-verify test relatively hard to pass when the number is relatively small and relatively easy to pass when the number is relatively large. Or, Nwl can be used to identify a next word line to program in the block.