A method includes forming a first transistor, a second transistor, a third transistor, and a fourth transistor over a substrate, wherein at least the second and third transistors include ferroelectric materials; forming an interlayer dielectric (ILD) layer over the first to fourth transistors; forming a first metal line over the ILD layer to interconnect drains of the second and third transistors and a gate of the fourth transistor; forming a second metal line over the ILD layer to interconnect a drain of the first transistor and gates of the second and third transistors; forming a write word line over the ILD layer and electrically connected to a gate of the first transistor but electrically isolated from the fourth transistor; forming a word line over the ILD layer and electrically connected to a source of the first transistor; and forming a bit line electrically connected to the fourth transistor.

A method includes forming a first transistor, a second transistor, a third transistor, and a fourth transistor over a substrate, wherein at least the second and third transistors include ferroelectric materials; forming an interlayer dielectric (ILD) layer over the first to fourth transistors; forming a first metal line over the ILD layer to interconnect drains of the second and third transistors and a gate of the fourth transistor; forming a second metal line over the ILD layer to interconnect a drain of the first transistor and gates of the second and third transistors; forming a write word line over the ILD layer and electrically connected to a gate of the first transistor but electrically isolated from the fourth transistor; forming a word line over the ILD layer and electrically connected to a source of the first transistor; and forming a bit line electrically connected to the fourth transistor.

A memory device is provided. The memory device comprises an internal clock generator configured to receive an external clock signal from a host and generate an internal clock signal in accordance with a chip enable signal, an internal enable signal generator configured to operate based on the internal clock signal and receive an external enable signal from the host and generate an internal enable signal, and a monitoring signal generator configured to output a monitoring signal that is generated based on at least one of the internal clock signal or the internal enable signal to the host.

A mixed-signal in-memory computing sub-cell only requires 9 transistors for 1-bit multiplication. A computing cell is constructed from a plurality of such sub-cells that share a common computing capacitor and a common transistor. Also proposed is a MAC array for performing MAC operations, which includes a plurality of the computing cells each activating the sub-cells therein in a time-multiplexed manner. Also proposed is a differential version of the MAC array with improved computation error tolerance and an in-memory mixed-signal computing module for digitalizing parallel analog outputs of the MAC array and for performing other tasks in the digital domain. An ADC block in the computing module makes full use of capacitors in the MAC array, thus allowing the computing module to have a reduced area and suffer from less computation errors. Also proposed is a method of fully taking advantage of data sparsity to lower the ADC block's power consumption.

A memory processing unit architecture can include a plurality of memory regions and a plurality of processing regions interleaved between the plurality of memory regions. The plurality of processing regions can be configured to perform computation functions of a model such as an artificial neural network. Data can be transferred between the computation functions in respective memory processing regions. In addition, the memory regions can be utilized to transfer data between a computation function in one processing region and a computation function in another processing region adjacent to the given memory region.

A static random access memory (SRAM) includes a bit cell including a p-type pass gate, a bit information path connected to the bit cell by the p-type pass gate, and a read multiplexer connected to the bit information path. The read multiplexer includes an n-type transistor configured to selectively couple the bit information path to a sense amplifier.

A static random access memory (SRAM) includes a bit cell including a p-type pass gate, a bit information path connected to the bit cell by the p-type pass gate, and a read multiplexer connected to the bit information path. The read multiplexer includes an n-type transistor configured to selectively couple the bit information path to a sense amplifier.

Embodiments of three-dimensional (3D) memory devices with a 3D NAND memory array having a plurality of pages, an on-die cache coupled to the memory array on a same chip and configured to cache a plurality of batches of program data between a host and the memory array, the on-die cache having SRAM cells, and a controller coupled to the on-die cache on the same chip. The controller is configured to check a status of an (N−2).sup.th batch of program data, N being an integer equal to or greater than 2, program an (N−1).sup.th batch of program data into respective pages in the 3D NAND memory array, and cache an N.sup.th batch of program data in respective space in the on-die cache as a backup copy of the N.sup.th batch of program data.

The present disclosure includes apparatuses and methods for acceleration of data queries in memory. An example apparatus includes an array of memory cells and processing circuitry. The processing circuitry is configured to receive, from a host, a query for particular data in the array of memory cells, wherein the particular data corresponds to a search key generated by the host, search portions of the array of memory cells for the particular data corresponding to the search key generated by the host, search portions of the array of memory cells for the particular data corresponding to the search key, determine data stored in the portions of the array of memory cells that corresponds more closely to the search key than other data stored in the portions of the array of memory cells, and transfer the data that corresponds more closely to the search key than the other data to the host.

According to one embodiment, a display device includes a pair of substrates including a display area in which pixels are arranged, pixel electrodes and memories provided in the pixels, signal lines supplied with digital signals, switching elements connecting the memories and the signal lines, scanning lines supplied with scanning signals, a first driver unit, and a second driver unit. The first driver unit is provided in a peripheral area around the display area, and supplies the digital signal to the signal line. The second driver unit is provided in the peripheral area, and supplies the scanning signal to the scanning line. In the display device, at least a part of the first driver unit is provided between the display area and the second driver unit.