Abstract: A method of forming a non-volatile memory device. The method forms a vertical stack of first polysilicon material and a second polysilicon material layer isolated by a dielectric material. The polysilicon material layers and the dielectric material are subjected to a first pattern and etch process to form a first wordline associated with a first switching device and a second wordline associated with a second switching device from the first polysilicon material layer, and a third wordline associated with a third switching device and a fourth wordline associated with a fourth switching device from the second polysilicon material. A via opening is formed to separate the first wordline from the second wordline and to separate the third wordline from the fourth wordline. An amorphous silicon switching material is deposited conformably overlying the via opening. A metal material fills the via opening and connects to a common bitline.

Abstract: Providing a memory array having an embedded source line driver is described herein. By way of example, the source line driver can comprise a dissipation line and a switching component that connects or disconnects the dissipation line with a source line of the memory array. When the switching component is activated, the dissipation line can provide a low resistance path from the source line to ground, as one example. Disclosed are circuits in which one or more dissipation lines are situated along a length of the source line, facilitating reduced variation in electrical characteristics (e.g., voltage drop) along the source line, improving regularity of memory operations for memory cells associated with the source line.

Abstract: Providing for a solid state memory cell having a resistive switching memory cell with rectifier characteristics is described herein. By way of example, the solid state memory cell can have one or more layers creating a resistive switching device capable of achieving and maintaining different electrical resistances in response to different voltages applied to the solid state memory cell. Moreover, the solid state memory cell can comprise two or more layers creating a solid state diode device electrically in series with the resistive switching device. The solid state diode device can be configured to permit very low current through the solid state memory cell at voltages less than a breakdown voltage or reverse breakdown voltage. The rectifier characteristics can mitigate sneak path currents in a crossbar memory array, or similar array, facilitating greater sensing margin, reduced likelihood of memory errors, greater die concentration, fast switching times, and other benefits.

Abstract: A non-volatile memory device programs memory cells in each row in a manner that minimizes the coupling of spurious signals. A control logic unit programs the cells in a row using a set of bit state assignments chosen by evaluating data that are to be written to the cells in the row. The control logic unit performs this evaluation by determining the number of cells in the row that will be programmed to each of a plurality of bit states corresponding to the write data. The control logic unit then selects a set of bit state assignments that will cause the programming level assigned to each bit state to be inversely proportional to the number of memory cells in the row that are programmed with the bit state. The selected set of bit states is then used to program the memory cells in the row.

Abstract: Providing for single and multi-bit error correction of electronic memory is described herein. As an example, error correction can be accomplished by establishing a suspect region between bit level distributions of a set of analyzed memory cells. The suspect region can define potential error bits for the distributions. If a bit error is detected for the distributions, error correction can first be applied to the potential error bits in the suspect region. By identifying suspected error bits and limiting initial error correction to such identified bits, complexities involved in applying error correction to all bits of the distributions can be mitigated or avoided, improving efficiency of bit error corrections for electronic memory.

Abstract: A non-volatile memory device is provided that uses one or more volatile elements. In some embodiments, the non-volatile memory device can include a resistive two-terminal selector that can be in a low resistive state or a high resistive state depending on the voltage being applied. A MOS (“metal-oxide-semiconductor”) transistor in addition to a capacitor or transistor acting as a capacitor can also be included. A first terminal of the capacitor can be connected to a voltage source, and the second terminal of the capacitor can be connected to the selector device. A floating gate of an NMOS transistor can be connected to the other side of the selector device, and a second NMOS transistor can be connected in series with the first NMOS transistor.

Abstract: Providing for improved sensing of non-volatile resistive memory to achieve higher sensing margins, is described herein. The sensing can leverage current-voltage characteristics of a volatile selector device within the resistive memory. A disclosed sensing process can comprise activating the selector device with an activation voltage, and then lowering the activation voltage to a holding voltage at which the selector device deactivates for an off-state memory cell, but remains active for an on-state memory cell. Accordingly, very high on-off ratio characteristics of the selector device can be employed for sensing the resistive memory, providing sensing margins not previously achievable for non-volatile memory.

Abstract: Providing for a field programmable gate array (FPGA) utilizing resistive random access memory (RRAM) technology is described herein. By way of example, the FPGA can comprise a switching block interconnect having parallel signal input lines crossed by perpendicular signal output lines. RRAM memory cells can be formed at respective intersections of the signal input lines and signal output lines. The RRAM memory cell can include a voltage divider comprising multiple programmable resistive elements arranged electrically in series across a VCC and VSS of the FPGA. A common node of the voltage divider drives a gate of a pass gate transistor configured to activate or deactivate the intersection. The disclosed RRAM memory can provide high transistor density, high logic utilization, fast programming speed, radiation immunity, fast power up and significant benefits for FPGA technology.

Abstract: Providing for a high performance and efficiency NAND architecture is described herein. By way of example, a NAND array is disclosed comprising memory cells having a 1 transistor-1 two-terminal memory device (IT-1D) arrangement. Memory cells of the NAND array can be arranged electrically in serial with respect to each other, from source to drain. Moreover, respective memory cells comprise a transistor component connected in parallel to a two-terminal memory device. In some embodiments, a resistance of the activated transistor component is selected to be substantially less than that of the two-terminal memory device, and the resistance of the deactivated transistor component is selected to be substantially higher than the two-terminal memory device. Accordingly, by activating or deactivating the transistor component, a signal applied to the memory cell can be shorted past the two-terminal memory device, or directed through the two-terminal memory device, respectively.

Abstract: A non-volatile memory device includes a word line extending along a first direction; a bit line extending along a second direction; a memory unit having a read transistor coupled to the bit line, at least one two-terminal memory cell, and a select transistor, the two-terminal memory cell having a first end coupled to the word line and a second end coupled to a gate of the read transistor. The second end of the two-terminal memory cell is coupled to a common node shared by a drain of the select transistor and the gate of the read transistor.

Abstract: A method of forming a non-volatile memory device. The method forms a vertical stack of first polysilicon material and a second polysilicon material layer isolated by a dielectric material. The polysilicon material layers and the dielectric material are subjected to a first pattern and etch process to form a first wordline associated with a first switching device and a second wordline associated with a second switching device from the first polysilicon material layer, and a third wordline associated with a third switching device and a fourth wordline associated with a fourth switching device from the second polysilicon material. A via opening is formed to separate the first wordline from the second wordline and to separate the third wordline from the fourth wordline. An amorphous silicon switching material is deposited conformably overlying the via opening. A metal material fills the via opening and connects to a common bitline.

Abstract: Providing for a non-volatile semiconductor memory architecture that achieves high read performance is described herein. In one aspect, an array of memory transistors arranged electrically in serial is configured to control a gate voltage of a pass transistor. The pass transistor, in turn, enables current flow between two metal bitlines of the semiconductor memory architecture. Accordingly, a relative voltage or relative current of the two metal bitlines can be measured and utilized to determine a program or erase state of a transistor of the serial array of transistors. In a particular aspect, a transistor with small capacitance is chosen for the pass transistor, resulting in a fast correspondence of the pass transistor gate voltage/current relative to transistor array current. This can equate to fast read times for the transistor array, based on differential sensing of the two metal bitlines.

Abstract: Providing for a field programmable gate array (FPGA) utilizing resistive random access memory (RRAM) technology is described herein. By way of example, the FPGA can comprise a switching block interconnect having parallel signal input lines crossed by perpendicular signal output lines. RRAM memory cells can be formed at respective intersections of the signal input lines and signal output lines. The RRAM memory cell can include a voltage divider comprising multiple programmable resistive elements arranged electrically in series across a VCC and VSS of the FPGA. A common node of the voltage divider drives a gate of a pass gate transistor configured to activate or deactivate the intersection. The disclosed RRAM memory can provide high transistor density, high logic utilization, fast programming speed, radiation immunity, fast power up and significant benefits for FPGA technology.

Abstract: A non-volatile memory device includes an array of memory units, each having resistive memory cells and a local word line. Each memory cell has a first and a second end, the second ends are coupled to the local word line of the corresponding memory unit. Bit lines are provided, each coupled to the first end of each resistive memory cell. A plurality of select transistors is provided, each associated with one memory unit and having a drain terminal coupled to the local word line of the associated memory unit. First and second global word lines are provided, each coupled to a control terminal of at least one select transistor. First and second source lines are provided, each coupled to a source terminal of at least one select transistor. The memory device is configured to concurrently read out all resistive memory cells in one selected memory unit in a read operation.

Abstract: A non-volatile memory device includes a word line extending along a first direction; a bit line extending along a second direction; a memory unit having a read transistor coupled to the bit line, at least one two-terminal memory cell, and a select transistor, the two-terminal memory cell having a first end coupled to the word line and a second end coupled to a gate of the read transistor. The second end of the two-terminal memory cell is coupled to a common node shared by a drain of the select transistor and the gate of the read transistor.

Abstract: A circuit for programming a resistive switching device includes a resistive switching device characterized by a programmable resistance, the resistive switching device comprising a first terminal, a second terminal, and a resistive switching element, a first circuit configured to supply a programming voltage to the resistive switching device and to supply a predetermined current to flow in the resistive switching device, and a second circuit coupled to the first circuit and to the resistive switching device, wherein the second circuit is configured to terminate the supply of the programming voltage to the resistive switching device when the predetermined current flows in the resistive switching device.

Abstract: A non-volatile variable capacitive device includes a capacitor defined over a substrate, the capacitor having an upper electrode and a resistive memory cell having a first electrode, a second electrode, and a switching layer provided between the first and second electrodes. The resistive memory cell is configured to be placed in a plurality of resistive states according to an electrical signal received. The upper electrode of the capacitive device is coupled to the second electrode of the resistive memory cell. The resistive memory cell is a two-terminal device.

Abstract: Providing for a two-terminal memory architecture that can mitigate sneak path current in conjunction with memory operations is described herein. By way of example, a voltage mimicking mechanism can be employed to dynamically drive un-selected bitlines of the memory architecture at a voltage observed by a selected bitline. According to these aspects, changes observed by the selected bitline can be applied to the un-selected bitlines as well. This can help reduce or avoid voltage differences between the selected bitline and the un-selected bitlines, thereby reducing or avoiding sneak path currents between respective bitlines of the memory architecture. Additionally, an input/output based configuration is provided to facilitate reduced sneak path current according to additional aspects of the subject disclosure.

Abstract: A method of forming a non-volatile memory device. A substrate is provided and a first dielectric material forms overlying the substrate. A first polysilicon material is deposited overlying the first dielectric material. A second dielectric material is deposited overlying the first polysilicon material. A second polysilicon material is deposited overlying the second dielectric material. A third dielectric material is formed overlying the second polysilicon material. The third dielectric material, the second polysilicon material, the second dielectric material, and the first polysilicon material is subjected to a first pattern and etch process to form a first wordline associated with a first switching device and a second wordline associated with a second switching device from the first polysilicon material, a third wordline and associated with a third switching device, and a fourth wordline associated with a fourth switching device from the second polysilicon material.

Abstract: Providing for capacitive programming of two-terminal memory devices is described herein. By way of example, a capacitance circuit can be precharged to a predetermined program voltage to facilitate programming one or more memory cells. The capacitance circuit can be disconnected from a power source and connected instead to the memory cell(s), enabling charge stored by the capacitance circuit to discharge through the memory cell(s). A current at the memory cell(s) can program the cell, while a total amount of discharge is limited to the charge stored by the capacitance circuit. Limiting the total charge can serve to also limit joule heating of the target memory cell, power consumption of a memory device, as well as other benefits.