The memory device of the electrically-erasable programmable read-only memory type comprises write circuitry designed to carry out a write operation in response to receiving a command for writing at least one selected byte in at least one selected memory word of the memory plane, the write operation comprising an erase cycle followed by a programming cycle, and configured for generating, during the erase cycle, an erase voltage in the memory cells of all the bytes of the at least one selected memory word, and an erase inhibit potential configured, with respect to the erase voltage, for preventing the erasing of the memory cells of the non-selected bytes of the at least one selected memory word, which are not the at least one selected byte.

In general, according to one embodiment, an output circuit includes first to third power supply lines, a pad, first to second transistors, and a first circuit. A first end of the first transistor is coupled to the first power supply line. A second end of the first transistor is coupled to the pad. A first end of the second transistor is coupled to the second power supply line. A second end of the second transistor is coupled to the pad. The first circuit is coupled to each of the third power supply line and a gate of the first transistor. In a first case, the first circuit applies a fourth voltage to the gate of the first transistor.

An integrated chip includes a first well region, second well region, and third well region disposed within a substrate. The second well region is laterally between the first and third well regions. An isolation structure is disposed within the substrate and laterally surrounds the first, second, and third well regions. A floating gate overlies the substrate and laterally extends from the first well region to the third well region. A dielectric structure is disposed under the floating gate. A bit line write region is disposed within the second well region and includes source/drain regions disposed on opposite sides of the floating gate. A bit line read region is disposed within the second well region, is laterally offset from the bit line write region by a non-zero distance, and includes source/drain regions disposed on the opposite sides of the floating gate.

A three-way switch array structure including N first connectors, M second connectors, N×M third connectors and N×M three-way switches is provided, each three-way switch has a first terminal, a second terminal, a third terminal, a first switch and a second switch. Each of first terminals is disposed on one of the first connectors, each of second terminals is disposed on one of the second connectors, and each of third terminals is disposed on one of the third connectors, the first switch is disposed between the first terminal and the third terminal, and the second switch is disposed between the second terminal and the third terminal, wherein N and M are positive integers greater than or equal to 1.

A memory apparatus and method of operation is provided. The apparatus includes a block of memory cells. Each of the memory cells is connected to one of a plurality of word lines and arranged in strings. Each of the memory cells is also configured to retain a threshold voltage corresponding to one of a plurality of data states and be erased in an erase operation. A control circuit is coupled to the word lines and the strings and is configured to identify ones of the strings having a faster relative erase speed compared to others of the strings. During the erase operation, the control circuit raises the threshold voltage of the memory cells associated with the ones of the strings having the faster relative erase speed while not raising the threshold voltage of the memory cells associated with the others of the strings.

A vertical NAND string in a channel-stacked 3D memory device may be programmed using ISPP scheme, wherein a preparation step is introduced immediately after each verification step and before the start of a corresponding verification step. During the preparation step, the electrons accumulated in the channel may be drained by the selected bit line for enhancing the coupling effect of the channel, thereby reducing program disturb and increasing program speed.

A memory device is provided. The memory device includes a first transistor and a second transistor connected in series with the first transistor. The second transistor is programmable between a first state and a second state. A bit line connected to the second transistor. A sense amplifier connected to the bit line. The sense amplifier is operative to sense data from the bit line. A feedback circuit connected to the sense amplifier, wherein the feedback circuit is operative to control a bit line current of the bit-line.

The invention relates to a two-bit memory cell structure, and an array architecture and a circuit structure thereof in an in-memory computing chip. The double-bit storage unit comprises three transistors which are connected in series, a selection transistor in the middle is used as a switch, and two charge storage transistors are symmetrically arranged on the two sides of the double-bit storage unit. A storage array formed by the double-bit storage unit is used for storing the weight of the neural network, and multiplication and accumulation operation of the neural network is carried out in a two-step current detection mode. According to the invention, leakage current can be effectively controlled, higher weight storage density and higher reliability are realized, and neural network operation with more practical significance is further realized.

Provided are a semiconductor device and a method of manufacturing the same. The semiconductor device includes a substrate, a first FET, and a second FET formed over the substrate. The substrate has a first surface and a second surface, and the first surface and the second surface form a step. The first FET comprises a first gate dielectric layer over the first surface of the substrate. The second FET comprises a second gate dielectric layer thinner than the first gate dielectric layer over the second surface of the substrate.

In some examples, an integrated circuit comprises a first plate, a second plate, and a dielectric layer disposed between the first and second plates, the first and second plates and the dielectric layer forming a vertical capacitor, wherein the first and second plates and the dielectric layer of the vertical capacitor are disposed on an isolation region of the integrated circuit.