A semiconductor storage device includes: a first memory cell and a second memory cell that are adjacent to each other and connected to each other in series; a first word line connected to the first memory cell; a second word line connected to the second memory cell; and a control circuit. The control circuit is configured to, in a first read operation to read a first bit stored in the first memory cell, apply a first voltage to the first word line, and then, apply a first read voltage lower than the first voltage, to the first word line, and apply a second voltage to the second word line, and then, apply a third voltage lower than the second voltage and higher than the first voltage, to the second word line. The third voltage is applied to the second word line after the first read voltage is applied to the first word line.

The present disclosure relates to a method for improving the reading and/or writing phase in storage devices including a plurality of non-volatile memory portions managed by a memory controller, comprising: providing at least a faster memory portion having a lower latency and higher throughput with respect to said non-volatile memory portions and being by-directionally connected to said controller; using said faster memory portion as a read and/or write cache memory for copying the content of memory regions including more frequently read or written logical blocks of said plurality of non-volatile memory portions.
A specific read cache architecture for a managed storage device is also disclosed to implement the above method.

A semiconductor device capable of performing high-speed read or high-reliability read is provided. A reading method of a NAND flash memory includes: pre-charging a sensing node through a voltage-supply node; discharging the sensing node to the voltage-supply node for a prescribed operation; recharging the sensing node by the voltage-supply node after the prescribed operation; and discharging a NAND string and sensing a memory cell.

A memory device includes a memory cell array, a plurality of bit lines, and a plurality of page buffers including a plurality of cache latches, exchanging data with the memory cell array through the plurality of bit lines, wherein the plurality of cache latches are arranged in a column direction in parallel with the plurality of bit lines and a row direction perpendicular to the plurality of bit lines, and have a two-dimensional arrangement of M stages in the column direction, where M is a positive integer not corresponding to 2.sup.L and L is zero or a natural number.

A method of cache programming of a NAND flash memory in a triple-level-cell (TLC) mode is provided. The method includes discarding a lower page of a first programming data from a first set of data latches in a plurality of page buffers when a first group of logic states are programmed and verified. The page buffers include the first, second and third sets of data latches configured to store the lower page, a middle page and an upper page of programming data, respectively. The method also includes uploading a lower page of second programming data to a set of cache latches, transferring the lower page of the second programming data from the set of cache latches to the second set of data latches after the discarding the middle page of the first programming data, and uploading a middle page of the second programming data to the set of cache latches.

Incoming host data is programmed to a first set of data blocks indicated by a first cursor of a memory sub-system. The first set of blocks is associated with a first write mode. A determination is made that a second set of blocks associated with a second write mode is available to store the incoming host data prior to closing one or more of the first set of blocks. The incoming host data is programmed to the second set of blocks in view of a second cursor of the memory sub-system. A media management operation is performed to close the one or more of the first set of blocks.

A nonvolatile memory device includes a memory cell array including memory cells and a page buffer circuit. The page buffer circuit includes page buffer units and cache latches. The cache latches are spaced apart from the page buffer units in a first horizontal direction, and correspond to respective ones of the plurality of page buffer units. Each of the page buffer units includes a pass transistor connected to each sensing node and driven in response to a pass control signal. The page buffer circuit being configured to perform a data transfer operation, based on performing a first data output operation to output data, provided from a first portion of page buffer units, from a first portion of cache latches to a data input/output (I/O) line, the data transfer operation configured to dump sensed data from a second portion of page buffer units to a second portion of cache latches.

The present disclosure relates to a method for improving the reading and/or writing phase in storage devices including a plurality of non-volatile memory portions managed by a memory controller, comprising: providing at least a faster memory portion having a lower latency and higher throughput with respect to said non-volatile memory portions and being by-directionally connected to said controller; using said faster memory portion as a read and/or write cache memory for copying the content of memory regions including more frequently read or written logical blocks of said plurality of non-volatile memory portions.

A specific read cache architecture for a managed storage device is also disclosed to implement the above method.

A semiconductor memory device according to an embodiment includes first memory cells, second memory cells, and a controller. A threshold voltage of each of the first memory cells and the second memory cells is included in one of first through sixteenth state. 8-bit data that includes a first through eighth bit is stored using a combination of a threshold voltage of the first memory cell and a threshold voltage of the second memory cell. The controller is configured to: apply in parallel a plurality of types of read voltages to each of the first memory cells and the second memory cells and externally output data confirmed based on first data read from the first memory cells and second data read from the second memory cells.

Methods, systems, and devices for a magnetic cache for a memory device are described. Magnetic storage elements (e.g., magnetic memory cells, such as spin-transfer torque (STT) memory cells or magnetic tunnel junction (MTJ) memory cells) may be configured to act as a cache for a memory array, where the memory array includes a different type of memory cells. The magnetic storage elements may be inductively coupled to access lines for the memory array. Based on this inductive coupling, when a memory value is written to or read from a memory cell of the array, the memory value may concurrently be written to a magnetic storage element based on associated current through an access line used to write or read the memory cell. Subsequent read requests may be executed by reading the memory value from the magnetic storage element rather than from the memory cell of the array.