A NAND flash memory array includes a select line having a first edge region containing a first portion of floating gate material and a second edge region containing a second portion of floating gate material, and having a central region between the first edge region and the second edge region where no floating gate material is present.

In one example, a system comprises an array comprising selected memory cells; an input block configured to apply, to each selected memory cell, a series of input signals to a terminal of the selected memory cell in response to a series of input bits; and an output block for generating an output of the selected memory cells, the output block comprising an analog-to-digital converter to convert current from the selected memory cells into a digital value, a shifter, an adder, and a register; wherein the shifter, adder, and register are configured to receive a series of digital values in response to the series of input bits, shift each digital value in the series of digital values based on a bit location of an input bit within the series of input bits, and add results of the shift operations to generate an output indicating values stored in the selected memory cells.

A flash memory device and method of making the same are disclosed. The flash memory device is located on a substrate and includes a floating gate electrode, a tunnel dielectric layer located between the substrate and the floating gate electrode, a smaller length control gate electrode and a control gate dielectric layer located between the floating gate electrode and the smaller length control gate electrode. The length of a major axis of the smaller length control gate electrode is less than a length of a major axis of the floating gate electrode.

A neural network device with synapses having memory cells each having a floating gate and a first gate over first and second portions of a channel region between source and drain regions, and a second gate over the floating gate or the source region. First lines each electrically connect the first gates in one of the memory cell rows, second lines each electrically connect the second gates in one of the memory cell rows, third lines each electrically connect the source regions in one of the memory cell rows, fourth lines each electrically connect the drain regions in one of the memory cell columns, and a plurality of transistors each electrically connected in series with one of the fourth lines. The synapses receive a first plurality of inputs as electrical voltages on gates of the transistors, and provide a first plurality of outputs as electrical currents on the third lines.

A non-volatile memory structure includes a semiconductor substrate and first and second memory devices on the semiconductor substrate. Each of the first and second memory devices includes a floating gate, a tunnelling insulator under the floating gate, an isolation layer over the floating gate, and at least one of a select gate and a control gate over the isolation layer. The non-volatile memory structure further includes an erase gate shared by the first and second memory devices, a source region under the erase gate, and a shallow trench isolation structure between the erase gate and the source region. The shallow trench isolation structure increases the number of write/erase cycles that can be performed by the non-volatile memory structure.

A non-volatile memory device includes at least one memory cell, and the memory cell includes a substrate, a trench, an erase gate, a control gate, and a floating gate. The trench is disposed in the substrate. The erase gate is disposed in the trench and includes a concave corner. The control gate is disposed on the substrate, and a bottom surface of the control gate is higher than a bottom surface of the erase gate. The floating gate is disposed on the substrate, and the floating gate includes a lower tip pointing toward the concave corner of the erase gate and extending beyond a sidewall of the trench.

A non-volatile memory device includes at least one memory cell, and the memory cell includes a substrate, a select gate, a control gate, an erase gate, and a floating gate. The select gate is disposed on the substrate. The control gate is disposed on the substrate and laterally spaced apart from the select gate. The erase gate is disposed on the substrate and laterally spaced apart from the control gate, and the erase gate includes a concave corner. The floating gate is covered with the control gate and the erase gate. The floating gate includes a convex corner which faces the concave corner of the erase gate, and the vertex of the floating gate is lower than a top surface of the select gate.

A semiconductor device includes a plurality of lines disposed on a semiconductor substrate, and remaining line patterns disposed spaced apart from the lines on extensions from the lines. The lines include first end-portions adjacent to the remaining line patterns. The remaining line patterns include second end-portions adjacent to the lines. The first end-portions and second end-portions are formed to have mirror symmetry with respect to each other.

A nonvolatile memory (NVM) bitcell includes a capacitor, a transistor, and a tunneling device. The capacitor, transistor, and tunneling device are each electrically coupled to different active regions and metal contacts. The three devices are coupled by a floating gate that traverses the three active regions. The tunneling device is used to program and erase the device, allowing for faster page erasure, and thus allows for rapid testing and verification of functionality. The transistor is used to read the logical state of the floating gate. The capacitor and floating gate are capacitively coupled together, removing the need for a separate selection device to perform read, write, and/or erase operations.

A method of forming a three-dimensional memory device includes forming a stack of alternating first and second material layers over a substrate, forming a memory opening through the stack, forming a memory film and a semiconductor channel in the memory opening, and forming backside recesses by removing the second material layers selective to the first material layers and the memory film, where an outer sidewall of the memory film is physically exposed within each backside recess. The method also includes forming at least one set of surfaces selected from silicon deposition inhibiting surfaces on the first material layers and silicon deposition promoting surfaces over the memory film in the back side recesses, selectively growing a silicon-containing semiconductor portion laterally within each backside recess, forming at least one blocking dielectric within the backside recesses, and forming conductive material layers by depositing a conductive material within the backside recesses.