Abstract: Techniques for using native and/or previously programmed resistive switching devices as one time programmable memory are discussed. On example method comprises allocating a set of resistive switching devices to be one time programmable memory; determining data to be stored in the set of resistive switching devices; for each resistive switching device of the set of resistive switching devices, assigning one of a first digital value or a second digital value to that resistive switching device, based on the data; and for each resistive switching device assigned the first digital value, permanently programming that resistive switching device via reverse formation.

Abstract: Systems, methods, and apparatus related to memory devices. In one approach, a memory device has a memory array including memory cells. A controller of the memory device evaluates background leakage in order to select a write voltage to apply to a memory cell when performing a programming operation. The write voltage is dynamically selected from two or more write voltages. These write voltages include a first write voltage that is a normal or default voltage, and a second write voltage that is a boosted write voltage. The controller applies a pre-sensing voltage and pre-read voltage to the memory cell, and determines first and second respective currents that result from applying these voltages. In response to determining that the first current exceeds a first threshold (indicating background leakage), and the second current is below a second threshold that is greater than the first threshold (indicating that the memory cell does not snap), the controller selects the second (boosted) write voltage.

Abstract: The present disclosure relates to circuits, systems, and methods of operation for a memory device. In an example, a memory device includes a plurality of memory cells, each memory cell having a variable impedance that varies in accordance with a respective data value stored therein; and a read circuit configured to read the data value stored within a selected memory cell based upon a variable time delay determination of a signal node voltage change corresponding to the variable impedance of the selected memory cell.

Abstract: An apparatus includes a control circuit that is configured to connect to an array of non-volatile memory cells. The control circuit includes a first plurality of data latches configured to connect to non-volatile memory cells of a first plane and a second plurality of data latches configured to connect to non-volatile memory cells of a second plane. The control circuit also includes a shared data transfer data latch configured for transfer of data with the first plurality of data latches and the second plurality of data latches.

Abstract: A layout of a delay circuit unit, a layout of a delay circuit, and a semiconductor memory are provided. The layout of the delay circuit unit includes multiple layout units arranged in an array and each forming a NOT-AND (NAND) gate circuit; here several layout units conforming to a first layout pattern are sequentially arranged in a first row of the array; and several layout units conforming to a second layout pattern are sequentially arranged in a second row of the array; here the first layout pattern is different from the second layout pattern, and the first layout pattern and the second layout pattern are such that the first row and the second row form a center-symmetrical structure.

Abstract: A circuit includes a memory array with SRAM cells connected in rows by word lines and in columns by bit lines. A row controller circuit simultaneously actuates, through a word line driver circuit for each row, word lines in parallel for an in-memory compute operation. A column processing circuit processes analog voltages developed on the bit lines in response to the simultaneous actuation to generate a decision output for the in-memory compute operation. A bit line precharge circuit generates a precharge voltage for application to each pair of bit lines. The precharge voltage has a first voltage level (not greater than a positive supply voltage for the SRAM cells) when the memory array is operating in a data read/write mode. The precharge voltage has a second voltage level (greater than the first voltage level) in advance of the simultaneous actuation of the word lines for the in-memory compute operation.

Abstract: A method for determining a sense boundary of a sense amplifier includes: writing the same data into the memory cells controlled by at least a pair of first word line on the left side and second word line on the right side corresponding to the sense amplifier; activating the first word line and precharging bit lines corresponding to the first word line; reading the data in the memory cells controlled by the corresponding second word line after a preset row precharge time; and determining a corresponding critical row precharge time as a row precharge time boundary value when the sense amplifier does not correctly read the data in the memory cells controlled by the second word line.

Abstract: The memory device includes a memory block with an array of memory cells. The memory device also includes control circuitry that is in communication with the memory cells. The control circuitry is configured to program a group of the memory cells in a programming operation that does not include verify to obtain a natural threshold voltage (nVt) distribution, calculate an nVt width of the nVt distribution, compare the nVt width to a threshold, and identify the memory block as being vulnerable to cross-temperature read errors in response to the nVt width exceeding the threshold.

Abstract: Disclosed are a weight memory device capable of supporting artificial neural network operation and a weight memory system using the same. A weight memory device according to an embodiment of the present invention includes: an input terminal; a common output terminal; and charge storage disposed between the input terminal and the common output terminal, and configured to store charge. In this case, the capacitance between the input terminal and the common output terminal is determined based on the amount of charge stored in the charge storage, and is quantified based on given data to be stored in the weight memory device.

Abstract: A memory device with adaptive sense time tables is disclosed. In order to maintain a desired (initial or preset) threshold voltage distribution, the sense time is adjusted as the program-erase cycle count increases. The program-erase cycle process tends to wear down memory cells, causing the QPW window to expand and the threshold voltage to widen. However, by adjusting (i.e., reducing) the sense time for increased program-erase cycles, the QPW window and the threshold voltage can be at least substantially maintained. Additionally, systems and methods for adjusting sense time based on die-to-die variations are also disclosed.

Abstract: Interconnections for modular die designs are disclosed. In one aspect, a die that is a chiplet is designed and tested for suitability. After approval of the chiplet design, multiple dies or chiplets may be coupled together within a multi-die package to form a package having desired computing capabilities. After assembly, each chiplet is provided a unique identifier, such as by setting a fuse. Based on the unique identifier, each chiplet is made aware of how interfaces to other chiplets are configured so that signals may be routed appropriately. Using modular chiplets in this fashion reduces testing requirements and non-recurring expenses while increasing flexibility for design options.

Abstract: Methods and apparatus for performing surface code computations using Auto-CCZ states. In one aspect, a method for implementing a delayed choice CZ operation on a first and second data qubit using a quantum computer includes: preparing a first and second routing qubit in a magic state; interacting the first data qubit with the first routing qubit and the second data qubit with the second routing qubit using a first and second CNOT operation, where the first and second data qubits act as controls for the CNOT operations; if a received first classical bit represents an off state: applying a first and second Hadamard gate to the first and second routing qubit; measuring the first and second routing qubit using Z basis measurements to obtain a second and third classical bit; and performing classically controlled fixup operations on the first and second data qubit using the second and third classical bits.

Abstract: A device is provided. The device includes a physical unclonable function (PUF) cell array. The PUF cell array includes multiple bit cells, and generates a PUF response output, in response to a challenge input, based on a data state of one bit cell in the bit cells. Each of the bit cells stores a bit data and includes a transistor having a control terminal coupled to a word line and a first terminal coupled to a source line, a first memory cell having a first terminal coupled to a first data line and a second terminal coupled to a second terminal of the transistor, and a second memory cell having a first terminal coupled to a second data line, different from the first data line, and a second terminal coupled to the second terminal of the first memory cell at the second terminal of the transistor.

Abstract: A memory device includes a plurality of bit lines extending in a first direction and arranged in a second direction; and a cell region including a plane which is coupled to the plurality of bit lines, wherein the plane is divided into a plurality of memory groups each including a plurality of partial pages to be disposed in a plurality of rows in the first direction.

Abstract: Disclosed is a system that comprises a memory device and a processing device, operatively coupled with the memory device, to perform operations that include, responsive to detecting a triggering event, selecting a family of memory blocks of the memory device, the selected family being associated with a set of bins, each bin associated with a plurality of read voltage offsets to be applied to base read voltages during read operations. The operations performed by the processing device further include calibration operations to determine data state metric values characterizing application of read voltage offsets of various bins. The operations performed by the processing device further include identifying, based on the determined data state metrics, a target bin and associating the selected family with the target bin.

Abstract: The present disclosure relates to a semiconductor structure and a manufacturing method thereof. The semiconductor structure includes: a substrate; a transistor, including a control terminal, a first terminal, and a second terminal; a first magnetic memory structure, a bottom electrode of which is electrically connected to the first terminal of the transistor; a second magnetic memory structure, a top electrode of which is electrically connected to the first terminal of the transistor, the bottom electrode of the first magnetic memory structure is located in a same layer with a bottom electrode of the second magnetic memory structure; a first bit line, electrically connected to a top electrode of the first magnetic memory structure; a second bit line, electrically connected to the bottom electrode of the second magnetic memory structure; and a selection line, electrically connected to a second terminal of the transistor.

Abstract: Disclosed herein is an apparatus that includes: a semiconductor substrate including first and second source regions coupled to a first power supply line and first and second drain regions coupled to a second power supply line, the first drain region being arranged between the first and second source regions, the second source region being arranged between the first and second drain regions; and gate electrodes including a first gate electrode arranged between the first source region and the first drain region, a second gate electrode arranged between the first drain region and the second source region, and a third gate electrode arranged between the second source region and the second drain region. The first and third gate electrodes are supplied with a first control signal. The second gate electrode is supplied with a second control signal.

Abstract: A semiconductor memory device includes a memory cell array that includes memory cells arranged in rows and columns, a row decoder that is configured to receive a row address, decode the row address, and adjust voltages of selection lines based on the decoded row address, a word line driver that is connected with the selection lines, is connected with the rows of the memory cells through word lines, and is configured to adjust voltages of the word lines in response to an internal clock signal and the voltages of the selection lines, and a detection circuit that is connected with the word lines and is configured to activate a detection signal in response to voltages of the word lines being identical at a specific timing.

Abstract: An Input/Output (I/O) circuit for a memory device is provided. The I/O circuit includes a charge integration circuit coupled to a bitline of the memory device. The charge integration circuit provides a sensing voltage based on a decrease of a voltage on the bitline. A comparator is coupled to the charge integration circuit. The comparator compares the sensing voltage with a reference voltage and provides an output voltage based on the comparison. A time-to-digital converter coupled to the comparator. The time-to-digital convertor converts a time associated with the output voltage to a digital value.

Abstract: Disclosed are various embodiments related to stacked memory devices, such as DRAMs, SRAMs, EEPROMs, ReRAMs, and CAMs. For example, stack position identifiers (SPIDs) are assigned or otherwise determined, and are used by each memory device to make a number of adjustments. In one embodiment, a self-refresh rate of a DRAM is adjusted based on the SPID of that device. In another embodiment, a latency of a DRAM or SRAM is adjusted based on the SPID. In another embodiment, internal regulation signals are shared with other devices via TSVs. In another embodiment, adjustments to internally regulated signals are made based on the SPID of a particular device. In another embodiment, serially connected signals can be controlled based on a chip SPID (e.g., an even or odd stack position), and whether the signal is an upstream or a downstream type of signal.