Memory devices have an array of elements in two or more dimensions. The memory devices use multiple access lines arranged in a grid to access the memory devices. Memory cells are located at intersections of the access lines in the grid. Drivers are used for each access line and configured to transmit a corresponding signal to respective memory cells of the plurality of memory cells via a corresponding access line. The memory devices also include compensation circuitry configured to determine which driving access lines driving a target memory cell of the plurality of memory cells has the most distance between the target memory cell and a respective driver. The plurality of access lines comprise the driving access lines. The compensation circuitry also is configured to output compensation values to adjust the voltages of the driving access lines based on a polarity of the voltage of the longer driving access line.

A memory circuit includes a bias voltage generator including a bias voltage node, an activation voltage generator including a resistive device, and a first amplifier, a drive circuit including a second amplifier including an input terminal coupled to the bias voltage node, and a resistive random-access memory (RRAM) array. The activation voltage generator and the first amplifier are configured to generate a portion of a bias voltage level on the bias voltage node based on a resistance of the resistive device, and the drive circuit is configured to output a drive voltage having the bias voltage level to the RRAM array.

A neuromorphic apparatus includes a three-dimensionally-stacked synaptic structure, and includes a plurality of unit synaptic modules, each of the plurality of unit synaptic modules including a plurality of synaptic layers, each of the plurality of synaptic layers including a plurality of stacked layers, and each of the plurality of unit synaptic modules further including a first decoder interposed between two among the plurality of synaptic layers. The neuromorphic apparatus further includes a second decoder that provides a level selection signal to the first decoder included in one among the plurality of unit synaptic modules to be accessed, and a third decoder that generates an address of one among a plurality of memristers to be accessed in a memrister array of one among the plurality of synaptic layers included in the one among the plurality of unit synaptic modules to be accessed.

Some embodiments provide a three-dimensional (3D) circuit that has data lines of one or more memory circuits on a different IC die than the IC die(s) on which the memory blocks of the memory circuit(s) are defined. In some embodiments, the 3D circuit includes a first IC die with a first set of two or more memory blocks that have a first set of data lines. The 3D circuit also includes a second IC die that is stacked with the first IC dies and that includes a second set of two or more memory blocks with a second set of data lines. The 3D circuit further includes a third IC die that is stacked with the first and second IC dies and that includes a third set of data lines, which connect through several z-axis connections with the first and second sets of data lines to carry data to and from the first and second memory block sets when data is being written to and read from the first and second memory block sets. The z-axis connections in some embodiments electrically connect circuit nodes in overlapping portions of the first and third IC dies, and overlapping portions of second and third IC dies, in order to carry data between the third set of data lines on the third IC die and the first and second set of data lines of the first and second of memory block sets on the first and second IC dies. These z-axis connections between the dies are very short as the dies are very thin. For instance, in some embodiments, the z-axis connections are less than 10 or 20 microns. The z-axis connections are through silicon vias (TSVs) in some embodiments.

The present disclosure includes apparatuses and methods for material implication operations in memory with reduced program voltages. An example apparatus can include an array of memory cells that further includes a first memory cell coupled to a first access line and to a first one of a plurality of second access lines and a second memory cell coupled to the first access line and to a second one of the plurality of second access lines. The circuitry can be configured to apply, across the second memory cell, a first voltage differential having a first polarity and a first magnitude. The first voltage differential reduces, if the second memory cell is programmed to a first data state, a magnitude of a drifted threshold voltage for programming the second memory cell to a second data state. The circuitry is further configured to apply, subsequent to the application of the first voltage differential, a first signal to the first access line. The circuitry is further configured to, while the first signal is being applied to the first access line, apply, subsequent to the application of the first voltage differential, a second voltage differential having a second polarity and the first magnitude across the first memory cell and apply a third voltage differential having the second polarity across the second memory cell. A material implication operation is performed as a result of the first, second, and third voltage differentials applied across the first and the second memory cells with a result of the material implication operation being stored on the second memory cell.

In accordance with some embodiments of the present disclosure, an apparatus for performing convolution operations is provided. The apparatus includes a first crossbar circuit comprising a first plurality of cross-point devices; a second crossbar circuit comprising a second plurality of cross-point devices; and a word line logic to apply input signals to the first crossbar circuit and the second crossbar circuit. The word line logic is configured to provide input signals representative of input data to be convolved using one or more two-dimensional convolution kernels and one or more depth-wise convolution kernels. The first crossbar circuit is configured to output a first plurality of output signals representative of a convolution of the input data and the two-dimensional convolution kernels. The second crossbar circuit is configured to output a second plurality of output signals representative of a convolution of the input data and the depth-wise convolution kernels.

The present disclosure relates to a chalcogenide material including germanium (Ge) with a first atomic percent, selenium (Se) with a second atomic percent that is at least twice the first atomic percent of the germanium, and indium (In) with a third atomic percent less the first atomic percent of the germanium.

An integrated circuit includes first and second arrays of resistors, and a plurality of interface circuits. Each resistor in the first array is electrically coupled between a corresponding first input conductive line among a plurality of first or second input conductive lines, and a corresponding first output conductive line among a plurality of first or second output conductive lines. Each resistor in the second array is electrically coupled between a corresponding second input conductive line among a plurality of second input conductive lines, and a corresponding second output conductive line among a plurality of second output conductive lines. Each interface circuit is electrically coupled between a corresponding first output conductive line and a corresponding second input conductive line. Each interface circuit is configured to receive a signal on the corresponding first output conductive line, and apply an analog voltage corresponding to the signal to the corresponding second input conductive line.

A memory access command to be performed on a die of a memory device is received, wherein the memory access command comprises a base partition number and a base page address. The memory access command is converted into a plurality of commands based on a number of partitions associated with the die. A respective partition number derived from the base partition number is determined for each command of the plurality of commands. A respective page address associated with each command of the plurality of commands is determined using the base page address. The plurality of commands is executed using, for each command of the plurality of commands, the respective partition number and the respective page address.

Disclosed is a memory device including a magnetic storage element. The memory device includes a memory cell array, a voltage generator, and a write driver. The memory cell array includes a first region and a second region. The memory device is configured to store a value of a first read current determined based on a value of a reference resistance for distinguishing a parallel state and an anti-parallel state of a programmed memory cell. The sensing circuit is configured to generate the first read current based on the value of the first read current and to perform a read operation on the first region based on the first read current.