Abstract: In one example, a neural network device comprises a first plurality of synapses configured to receive a first plurality of inputs and to generate therefrom a first plurality of outputs, wherein the first plurality of synapses comprises a plurality of memory cells, each of the plurality of memory cells configured to store a weight value corresponding to a number of electrons on its floating gate and the plurality of memory cells are configured to generate the first plurality of outputs based upon the first plurality of inputs and the stored weight values.

Abstract: A power device includes a substrate, an ion well in the substrate, a body region in the ion well, a source doped region in the body region, a drain doped region in the ion well, and gates on the substrate between the source doped region and the drain doped region. The gates include a first gate adjacent to the source doped region, a second gate adjacent to the drain doped region, and a stacked gate structure between the first gate and the second gate.

Abstract: The memory device includes a chip with circuitry, a plurality of memory blocks, and a plurality of bit lines. The memory blocks include an array of memory cells, and the circuitry either overlies or underlies the array of memory cells. The bit lines are divided into two portions that are electrically connected with one another via at least one transistor so that at least one portion of each bit line can be charged independently of the other portion of the same bit line.

Abstract: A novel semiconductor device is provided. A structure body extending in a first direction, a first conductor extending in a second direction, and a second conductor extending in the second direction are provided. In a first intersection portion where the structure body and the first conductor intersect with each other, a first insulator, a first semiconductor, a second insulator, a second semiconductor, a third insulator, a fourth insulator, and a fifth insulator are provided concentrically around a third conductor. In a second intersection portion where the structure body and the second conductor intersect with each other, the first insulator, the first semiconductor, the second insulator, a fourth conductor, the second semiconductor, and the third insulator are provided concentrically around the third conductor.

Abstract: A data coding device may include a raw data storage configured to store raw data of which the total number of bits is 2N, a previous data storage configured to store previous data output before the raw data, a counter configured to count the number of reference data bits included in the raw data, and a data output circuit configured to invert and output the raw data according to a comparison result with the previous data when the number of reference data bits included in the raw data is N, and invert and output the raw data according to the number of reference data bits included in the raw data when the number of reference data bits included in the raw data is not N.

Abstract: A method of forming an array of memory cells includes forming lines of covering material that are elevationally over and along lines of spaced sense line contacts. Longitudinal orientation of the lines of covering material is used in forming lines comprising programmable material and outer electrode material that are between and along the lines of covering material. The covering material is removed over the spaced sense line contacts and the spaced sense line contacts are exposed. Access lines are formed. Sense lines are formed that are electrically coupled to the spaced sense line contacts. The sense lines are angled relative to the lines of spaced sense line contacts and relative to the access lines. Other embodiments, including structure independent of method, are disclosed.

Abstract: A semiconductor storage device includes a semiconductor substrate including a first region, a second region, and a third region, located apart from each other in such an order in a first direction in an element region. Each of the first to third regions including a source and/or drain region. The semiconductor storage device further includes a first conductor layer provided above the element region and having a first opening; a second conductor layer provided above the element region, having a second opening, and located apart from the first conductor layer in the first direction; a first contact, in the first opening, that is connected to the first region; a second contact, in the second opening, that is connected to the third region; a first memory cell connected to the first contact; and a second memory cell connected to the second contact.

Abstract: A multi-time programmable non-volatile memory cell includes: a deep N-well, and first, second, third P-wells or a first N-well located in parallel to each other in the deep N-well, where a control capacitor and a tunneling capacitor are located in the first P-well and the second P-well, respectively, and each of the control capacitor and the tunneling capacitor includes one or two N-type coupling regions in the P-well; one floating-gate transistor is located in the third P-well or the first N-well, the floating-gate transistor including a polysilicon floating gate and its underlying gate oxide; and the floating gate of the floating-gate transistor and its gate oxide extend along a direction perpendicular to the parallel P-wells to cover the control capacitor and the tunneling capacitor, respectively forming an upper plate and a gate oxide of the control capacitor and the tunneling capacitor.

Abstract: Some implementations described herein provide a semiconductor structure. The semiconductor structure includes a first terminal coupled to a substrate of the semiconductor structure. The first terminal comprises a tunneling layer formed on the substrate, a first conductive structure formed on the tunneling layer, and a dielectric structure formed on a top surface and on a first curved side surface of the first conductive structure. The semiconductor structure includes a second terminal coupled to the substrate. The second terminal comprises a second conductive structure formed on an isolation structure. The second conductive structure has a second curved side surface, and the dielectric structure is disposed between the first curved side surface and the second curved side surface.

Abstract: A preparation method of a semiconductor structure includes: providing a base; forming several bit lines arranged in parallel and at intervals on the base, which extend in a first direction; forming capacitor contact material layers between adjacent bit lines, upper surfaces of which are lower than upper surfaces of the bit lines; forming filling medium layers on the capacitor contact material layers; forming several first mask patterns arranged in parallel and at intervals on the filling medium layers and the bit lines, which extend in a second direction that intersects with the first direction; patterning the filling medium layers based on the first mask patterns to form several grooves in the filling medium layers; forming second mask patterns in the grooves; and patterning the capacitor contact material layers based on the second mask patterns to form several cylindrical capacitor contact structures arranged in parallel and at intervals.

Abstract: Some embodiments include a ferroelectric transistor having an active region which includes a first source/drain region, a second source/drain region vertically offset from the first source/drain region, and a channel region between the first and second source/drain regions. A first conductive gate is operatively adjacent to the channel region of the active region. Insulative material is between the first conductive gate and the channel region. A second conductive gate is adjacent to the first conductive gate. Ferroelectric material is between the first and second conductive gates. Some embodiments include integrated memory. Some embodiments include methods of forming integrated assemblies.

Abstract: An array of programmable memory includes a first floating gate and a second floating gate disposed on a substrate along a first direction, two spacers disposed between and parallel to the first floating gate and the second floating gate, a first word line sandwiched by one of the spacers and the adjacent first floating gate, and a second word line sandwiched by the other one of the spacers and the adjacent second floating gate, and two first spacers disposed on the substrate, wherein one of the first spacer is disposed between the first word line and the first floating gate, and another spacer is disposed between the second word line and the second floating gate, wherein each spacer has substantially the same shape as each first spacer.

Abstract: A multi time program device with a power switch and a non-volatile memory implementing the power switch for multi time program is provided. The device performs a program operation or an erase operation of a non-volatile memory cell in a non-volatile memory device.

Abstract: A semiconductor arrangement and method of forming the same are described. A semiconductor arrangement includes a first gate structure on a first side of an active area and a second gate structure on a second side of the active area, where the first gate structure and the second gate structure share the active area. A method of forming the semiconductor arrangement includes forming a deep implant of the active area before forming the first gate structure, and then forming a shallow implant of the active area. Forming the deep implant prior to forming the first gate structure alleviates the need for an etching process that degrades the first gate structure. The first gate structure thus has a desired configuration and is able to be formed closer to other gate structures to enhance device density.

Abstract: A method of improving endurance of a NOR flash is provided. The NOR flash includes a substrate, a well formed in the substrate, a tunnel oxide layer, a floating gate, a dielectric layer, and a control gate sequentially stacked on the substrate, and a source and a drain formed in the well. The method includes the following steps. An erase time of the NOR flash is detected. In the case where the erase time exceeds a predetermined value, the source is brought into a floating state, a negative voltage is applied to the control gate, and a positive voltage is applied to the well to perform Joule heating on a drain side.

Abstract: Embodiments disclosed herein include a semiconductor structure. The semiconductor structure may include a magnetoresistive random access memory (MRAM) cell with a memory array landing pad contacting a first bottom metal level contact and an MRAM pillar electrically connected to the memory array landing pad. The semiconductor structure may also include a logic interconnect contacting a second bottom metal level contact and a dielectric cap above the MRAM cell and the logic interconnect. The MRAM cell and logic interconnect may be electrically connected to a top metal level through the dielectric cap.

Abstract: Methods, systems, and devices for decoder architecture for memory device are described. An apparatus includes a memory array having a memory cell and an access line coupled with the cell and a decoder having a first stage and a second stage. The decoder supplying a first voltage during a first access operation and a second voltage during a second access operation to the access line. The second stage of the decoder includes a first transistor that supplies the first voltage based on a third voltage at the source of the first transistor exceeding a fourth voltage at a gate of the first transistor and a first threshold voltage. The second stage includes a second transistor that supplies the second voltage based on a fifth voltage at a gate of the second transistor exceeding a sixth voltage at the source of the second transistor and a second threshold voltage.

Abstract: This disclosure is directed to methods for performing operations on a memory device. The memory device can include a bottom select gate, a plate line above the bottom select gate, a word line above the plate line, a pillar extending through the bottom select gate, the plate line, and the word line, a source line under the pillar, a drain cap above the pillar and a bit line formed above the drain cap. The method can include applying a first positive voltage bias to the bottom select gate and applying a second positive voltage bias to the word line. The method can also include applying a third positive voltage bias to the bit line after the word line reaches the second positive voltage bias. The method can further include applying a ground voltage to the word line and applying the ground voltage to the bit line.

Abstract: A memory device and method of making the same are disclosed. The memory device includes transistor devices located in both a memory region and a logic region of the device. Transistor devices in the memory region include sidewall spacers having a first oxide layer over a side surface of a gate structure, a first nitride layer over the first oxide layer, a second oxide layer over the first nitride layer, and a second nitride layer over the second oxide layer. Transistor devices in the logic region include sidewall spacers having a first oxide layer over a side surface of a gate structure, a first nitride layer over the first oxide layer, and a second nitride layer over the first nitride layer.

Abstract: A memory device includes a source element, a drain element, channel layers, control electrode layers, and a memory layer. The channel layers are individually electrically connected between the source element and the drain element. Memory cells are defined in the memory layer between the control electrode layers and the channel layers.

Abstract: An electronic device includes a semiconductor memory. A method for fabricating the electronic device includes forming a first memory cell extending vertically from a surface of substrate and having a first upper portion that protrudes laterally, forming a second memory cell extending vertically from the surface of the substrate and having a second upper portion that protrudes laterally towards the first upper portion, and forming a liner layer over the first and second memory cells, the liner layer having a first portion disposed over the first upper portion and a second portion disposed over the second upper portion, the first and second portions of the liner layer contacting each other.

Abstract: A circuit for in-memory multiply-and-accumulate functions includes a plurality of NAND blocks. A NAND block includes an array of NAND strings, including B columns and S rows, and L levels of memory cells. W word lines are coupled to (B*S) memory cells in respective levels in the L levels. A source line is coupled to the (B*S) NAND strings in the block. String select line drivers supply voltages to connect NAND strings on multiple string select lines to corresponding bit lines simultaneously. Word line drivers are coupled to apply word line voltages to a word line or word lines in a selected level. A plurality of bit line drivers apply input data to the B bit lines simultaneously. A current sensing circuit is coupled to the source line.

Abstract: A non-volatile memory has an array of non-volatile memory cells, first reference word lines and second reference word lines, and sense amplifiers. The sense amplifiers read system data, that has been written to supplemental non-volatile memory cells of the first reference word lines, using comparison of the supplemental non-volatile memory cells of the first reference word lines to supplemental non-volatile memory cells of the second reference word lines. Status of erasure of the non-volatile memory cells of the array is determined based on reading the system data.

Abstract: A storage device including a nonvolatile memory device that includes a nonvolatile memory cell array including a string including first and second memory cells stacked sequentially, and an OTP memory cell array that stores reference count values, the first and second memory cells respectively connected to first and second word lines; a controller including a processor that generates a read command for the first memory cell; a read level generator including a counter that receives the read command and calculates an off-cell count value of memory cells connected to the second word line, and a comparator that receives a first reference count value from the OTP memory cell array, compares the off-cell count value with the first reference count value to determine a threshold voltage shift of the second memory cell, and determines a read level of the first memory cell based on the threshold voltage shift.

Abstract: A semiconductor structure includes a substrate, word lines, bit line contact plugs, and first isolation layers. The word lines are located in the substrate. A bit line contact hole is provided between two adjacent word lines. The bit line contact plugs are located in the bit line contact holes. The first isolation layers are located on side walls of the bit line contact holes and cover side walls of the bit line contact plugs.

Abstract: A memory device and method of making the same are disclosed. The memory device includes transistor devices located in both a memory region and a logic region of the device. Transistor devices in the memory region include sidewall spacers having a first oxide layer over a side surface of a gate structure, a first nitride layer over the first oxide layer, a second oxide layer over the first nitride layer, and a second nitride layer over the second oxide layer. Transistor devices in the logic region include sidewall spacers having a first oxide layer over a side surface of a gate structure, a first nitride layer over the first oxide layer, and a second nitride layer over the first nitride layer.

Abstract: A device is disclosed herein. The device includes at least two transmit portions and at least one contact portion. Each of the at least two transmit portions is configured to receive a bit line signal. The at least one contact portion is couple to the at least two transmit portions respectively and configured to transmit the bit line signals from the least two transmit portions to a source line.

Abstract: A semiconductor device includes a substrate. The semiconductor device further includes a circuit layer over the substrate. The semiconductor device further includes a test line electrically connected to the circuit layer. The semiconductor device further includes a capacitor on the substrate. The capacitor includes a first conductor, wherein the first conductor is on a portion of the substrate exposed by the circuit layer. The capacitor further includes an insulator surrounding the first conductor.

Abstract: A method of forming a semiconductor structure includes forming first to third sacrificial layers on a substrate including a memory cell area and a peripheral area with a word line area. The second and third sacrificial layers in the word line area are removed to expose the top surface of the first sacrificial layer. The first sacrificial layer in the word line area and the third sacrificial layer in the memory cell area are removed. A word line dielectric layer and a first conductive layer are formed on the substrate in the word line area. The first and second sacrificial layers in the memory cell area are removed. A tunneling dielectric layer is formed on the substrate in the memory cell area. The thickness of the tunneling dielectric layer is smaller than the thickness of the word line dielectric layer.

Abstract: A semiconductor device includes a stack structure including conductive patterns spaced apart from each other, a channel structure penetrating the stack structure, and a slit insulating layer penetrating the stack structure. Air gaps are defined between the conductive patterns. The slit insulating layer includes a first interposition part covering a sidewall of one of the conductive patterns and a second interposition part covering one of the air gaps from the side. A smallest width of the second interposition part is smaller than a smallest width of the first interposition part.

Abstract: There are provided a semiconductor memory device and a manufacturing method thereof. The semiconductor memory device includes: a cell stack structure surrounding a first channel structure and a second channel structure; a first source select line overlapping with a first region of the cell stack structure and surrounding the first channel structure; and a second source select line overlapping with a second region of the cell stack structure and surrounding the second channel structure. Each of the first source select line and the second source select line includes a first select gate layer overlapping with the cell stack structure, a second select gate layer disposed between the first select gate layer and the cell stack structure, and a third select gate layer disposed between the first select gate layer and the second select gate layer.

Abstract: Disclosed in the present invention is a method for predicting a delay at multiple corners for a digital integrated circuit, which is applicable to the problem of timing signoff at multiple corners. In the aspect of feature engineering, a path delay relationship at adjacent corners is extracted by using a dilated convolutional neural network (Dilated CNN), and learning is performed by using a bi-directional long short-term memory model (Bi-directional Long Short-Term Memory, BLSTM) to obtain topology information of a path. Finally, prediction results of a path delay at a plurality of corners are obtained by using an output of a multi-gate mixture-of-experts network model (Multi-gate Mixture-of-Experts, MMoE).

Abstract: Numerous embodiments of a precision programming algorithm and apparatus are disclosed for precisely and quickly depositing the correct amount of charge on the floating gate of a non-volatile memory cell within a vector-by-matrix multiplication (VMM) array in an artificial neural network. Selected cells thereby can be programmed with extreme precision to hold one of N different values.

Abstract: A semiconductor die comprises: a first semiconductor device and a second semiconductor device. The first semiconductor device comprises a first device portion comprising a first sub-array of memory devices, and a first interface portion located adjacent to the first device portion in a first direction. The first interface portion has a staircase profile in a vertical direction. The second semiconductor device comprises a second device portion adjacent to the first device portion in the first direction opposite the first interface portion. The second device portion comprises a second sub-array of memory devices, and a second interface portion located adjacent to the first device portion in the first direction opposite the first interface portion. The second interface portion also has a staircase profile in the vertical direction. The first semiconductor device is electrically isolated from the second semiconductor device.

Abstract: Semiconductor devices and methods are provided. A semiconductor device of the present disclosure includes a bias source, a memory cell array including a first region adjacent to the bias source and a second region away from the bias source, and a conductive line electrically coupled to the bias source, a first memory cell in the first region and a second memory cell in the second region. The first memory cell is characterized by a first alpha ratio and the second memory cell is characterized by a second alpha ratio smaller than the first alpha ratio.

Abstract: A semiconductor device is disclosed. The semiconductor device includes a substrate including a semiconductor material. The semiconductor device includes a conduction channel of a transistor disposed above the substrate. The conduction channel and the substrate include a similar semiconductor material. The semiconductor device includes a source/drain region extending from an end of the conduction channel. The semiconductor device includes a dielectric structure. The source/drain region is electrically coupled to the conduction channel and electrically isolated from the substrate by the dielectric structure.

Abstract: A semiconductor storage device includes a substrate, a first wiring, a second wiring, a third wiring, a fourth wiring, a charge storage unit. The first wiring extends in a first direction along a surface of the substrate. The second wiring is aligned with the first wiring in a second direction intersecting with the first direction and extends in the first direction. The third wiring is in contact with the first wiring and the second wiring and includes a semiconductor. The fourth wiring is located between the first wiring and the second wiring, extends in a third direction intersecting with the first direction and the second direction, and is aligned with the third wiring in at least the first direction. The charge storage unit is located between the third wiring and the fourth wiring.

Abstract: An EEPROM memory integrated circuit includes memory cells arranged in a memory plane. Each memory cell includes an access transistor in series with a state transistor. Each access transistor is coupled, via its source region, to the corresponding source line and each state transistor is coupled, via its drain region, to the corresponding bit line. The floating gate of each state transistor rests on a dielectric layer having a first part with a first thickness, and a second part with a second thickness that is less than the first thickness. The second part is located on the source side of the state transistor.

Abstract: Disclosed is a three-dimensional flash memory including a back gate, which includes word lines extended and formed in a horizontal direction on a substrate so as to be sequentially stacked, and strings penetrating the word lines and extended and formed in one direction on the substrate. Each of the strings includes a channel layer extended and formed in the one direction, and a charge storage layer extended and formed in the one direction to surround the channel layer, the channel layer and the charge storage layer constitute memory cells corresponding to the word lines, and the channel layer includes a back gate extended and formed in the one direction, with at least a portion of the back gate surrounded by the channel layer, and an insulating layer extended and formed in one direction between the back gate and the channel layer.

Abstract: A memory cell arrangement is provided that may include: a plurality of first control lines; a plurality of second control lines; a plurality of third control lines; each of a plurality of memory cell sets includes memory cells and is assigned to a corresponding one of the plurality of first control lines and includes at least a first memory cell subset addressable via the corresponding first control line, a corresponding one of the plurality of second control lines, and the plurality of third control lines, and at least a second memory cell subset addressable via the corresponding first control line, the plurality of second control lines, and a corresponding one of the plurality of third control lines. The corresponding one of the plurality of third control lines addresses the second memory cell subset of each memory cell set of the plurality of memory cell sets.

Abstract: A semiconductor device includes a non-volatile memory. The non-volatile memory includes a first dielectric layer disposed on a substrate, a floating gate disposed on the dielectric layer, a control gate, a second dielectric layer disposed between the floating gate and the control gate, sidewall spacers disposed on opposing sides of a stacked structure including the floating gate, the second dielectric layer and the control gate, and an erase gate and a select gate disposed on sides of the stacked structure, respectively. An upper surface of the erase gate and one of the sidewall spacers in contact with the erase gate form an angle ?1 at a contact point of the upper surface of the erase gate and the one of the sidewall spacers, where 90°<?1<115° measured from the upper surface of the erase gate.

Abstract: Some embodiments include an integrated assembly with a semiconductor channel material having a boundary region where a more-heavily-doped region interfaces with a less-heavily-doped region. The more-heavily-doped region and the less-heavily-doped region have the same majority carriers. The integrated assembly includes a gating structure adjacent the semiconductor channel material and having a gating region and an interconnecting region of a common and continuous material. The gating region has a length extending along a segment of the more-heavily-doped region, a segment of the less-heavily-doped region, and the boundary region. The interconnecting region extends laterally outward from the gating region on a side opposite the semiconductor channel region, and is narrower than the length of the gating region. Some embodiments include methods of forming integrated assemblies.

Abstract: A flash device and a manufacturing method thereof. The method comprises: providing a substrate, and forming, on the substrate, a floating gate polycrystalline layer, a floating gate oxide layer, and a tunneling oxide layer; wherein the floating gate polycrystalline layer is formed on the substrate, the floating gate oxide layer is formed between the substrate and the floating gate polycrystalline layer, a substrate region at one side of the floating gate polycrystalline layer is a first substrate region, a substrate region at the other side of the floating gate polycrystalline layer is a second substrate region; forming, on the tunneling oxide layer, located in the first substrate region, a continuous non-conductive layer, the non-conductive layer extending to the tunneling oxide layer at a side wall of the floating gate polycrystalline layer; and forming, on the tunneling oxide layer, a polysilicon layer.

Abstract: Electronic apparatus and methods of forming the electronic apparatus may include one or more charge trap structures for use in a variety of electronic systems and devices, where each charge trap structure includes a dielectric barrier between a gate and a blocking dielectric on a charge trap region of the charge trap structure. In various embodiments, a void is located between the charge trap region and a region on which the charge trap structure is disposed. In various embodiments, a tunnel region separating a charge trap region from a semiconductor pillar of a charge trap structure, can be arranged such that the tunnel region and the semiconductor pillar are boundaries of a void. Additional apparatus, systems, and methods are disclosed.

Abstract: In a semiconductor storage device including a plurality of memory cells formed at a laminated substrate including a support layer, an insulating layer on the support layer, and a semiconductor layer on the insulating layer, the plurality of memory cells each include a floating gate transistor and a selection transistor. The floating gate transistor includes a first source region, a first drain region, a first body region, a first body contact region, a floating gate insulating film, and a floating gate electrode, and the selection transistor includes a second source region, a second drain region, a second body region, a second body contact region insulated from the first body contact region, a selection gate insulating film, and a selection gate electrode.

Abstract: A semiconductor memory cell includes a floating body region configured to be charged to a level indicative of a state of the memory cell; a first region in electrical contact with said floating body region; a second region in electrical contact with said floating body region and spaced apart from said first region; and a gate positioned between said first and second regions. The cell may be a multi-level cell. Arrays of memory cells are disclosed for making a memory device. Methods of operating memory cells are also provided.

Abstract: Memory might include an array of memory cells having a plurality of strings of series-connected split-gate memory cells each including a primary memory cell portion and an assist memory cell portion, a plurality of primary access lines each connected to a control gate of the primary memory cell portion of a respective split-gate memory cell of each string of series-connected split-gate memory cells of the plurality of strings of series-connected split-gate memory cells, and a plurality of assist access lines each connected to a control gate of the assist memory cell portion of its respective split-gate memory cell of each string of series-connected split-gate memory cells of the plurality of strings of series-connected split-gate memory cells.

Abstract: A memory system includes a memory device having a plurality of memory blocks for storing data, and a controller configured to perform an erase operation including plural unit erase operations to erase data stored in at least one target memory block included in the plurality of memory blocks. The controller can be configured to perform at least some of the plural unit erase operations onto the at least one target memory block before the at least one target memory block allocated for storing data.

Abstract: Technologies for scrambling functions in a column-addressable memory architecture includes a device having a memory and a circuitry. The memory includes a matrix storing individually addressable bit data, and the matrix is formed by rows and columns. The circuitry is to receive a request to perform a write operation of one or more bit values to one of the columns. The circuitry is further to determine a scrambler state at each location of the column, the location corresponding to a respective row and column index. The scrambler state is indicative of a function used to determine a value at the respective column location. Each of the bit values is scrambled as a function of the scrambler state for the respective column location and written thereto.

Abstract: Some embodiments include a ferroelectric transistor having an active region which includes a first source/drain region, a second source/drain region vertically offset from the first source/drain region, and a channel region between the first and second source/drain regions. A first conductive gate is operatively adjacent to the channel region of the active region. Insulative material is between the first conductive gate and the channel region. A second conductive gate is adjacent to the first conductive gate. Ferroelectric material is between the first and second conductive gates. Some embodiments include integrated memory. Some embodiments include methods of forming integrated assemblies.