Abstract: A static random-access memory (SRAM) includes a SRAM cell module, comprising a plurality of SRAM cell partitions, and an initialization register, containing data configured to control initialization of at least some of the plurality of partitions during an initialization phase. The SRAM also includes a control module coupled with the SRAM cell module and the initialization register, configured to read the initialization register during the initialization phase, and to selectively initialize a portion of the plurality of SRAM cell partitions, based at least in part on the data contained within the initialization register.

Abstract: A two-bit memory device having a layer structure containing in order a bottom layer, a molecular layer containing a chiral compound having at least one polar functional group, and a top layer, which is electrically conductive and ferromagnetic. The chiral compound acts as a spin filter for electrons passing through the molecular layer. The chiral compound is of flexible conformation and has a conformation-flexible molecular dipole moment. An electrical resistance of the layer structure for an electrical current running from the bottom layer to the top layer has at least four distinct states which depend on the magnetization of the top layer and on the orientation of the conformation-flexible dipole moment of the chiral compound. Furthermore, a method for operating the two-bit memory device and an electronic component containing at least one two-bit memory device.

Abstract: Technology is disclosed herein for sensing memory cells while compensating for resistance along an electrical pathway between a voltage driver and a control line connected to the memory cells. A control circuit provides a voltage from the voltage driver over a first electrical pathway to a control line in a first block and a second electrical pathway to a control line in a second block. The control circuit senses first memory cells in the first block and the second memory cells in the second block while compensating for a difference in resistance of the first and second electrical pathways. In one aspect, the control circuit discharges a first sense node for a different period of time than a second sense node to compensate for the difference in resistance. Compensating for the difference in resistance compensates for a different IR drop of the electrical pathways.

Abstract: A memory device and an operation method thereof for performing a multiply-accumulate operation are provided. The memory device includes at least one memory string, a plurality of data lines and a string line. The memory string includes a plurality of unit cells having a plurality of stored values. The data lines are respectively connected to the unit cells to receive a plurality of data signals having a plurality of inputting values. When the data signals are inputted into the unit cells, a plurality of nodes among the unit cells are kept at identical voltages. The string line is connected to the memory string to receive a sensing signal and obtain a measured value representing a sum-of-product result of the inputting values and the stored values. The data signals and the sensing signal are received at different time.

Abstract: The present disclosure provides a sense amplification structure and a memory architecture. The sense amplification structure includes: a first PMOS transistor provided with a gate connected to a second readout bit line and a source connected to a first signal terminal; a first NMOS transistor provided with a gate connected to an initial bit line; a drain of the first PMOS transistor and a drain of the first NMOS transistor being connected to a first complementary readout bit line; a second PMOS transistor provided with a gate connected to the second complementary readout bit line; a second NMOS transistor provided with a gate connected to an initial complementary bit line and a source connected to a second signal terminal; a drain of the second PMOS transistor and a drain of the second NMOS transistor being connected to the first readout bit line.

Abstract: A sense amplifier (SA), a memory and a control method are provided. The SA includes an amplifying module, configured to amplify voltage difference between a BL and a BLB when the SA is in an amplifying stage; a controllable power module, connected to the amplifying module and configured to stop providing power to the amplifying module when the SA is in a writing stage, to enable the amplifying module to stop working; and a writing module, connected to the BL and the BLB and configured to pull the voltage difference between the BL and the BLB according to data to be written when the SA is in the writing stage. The solution may ensure the successful data writing in a storage unit in a case that a writing circuit has weak drive capability.

Abstract: A semiconductor storage device includes: a first memory cell and a second memory cell that are adjacent to each other and connected to each other in series; a first word line connected to the first memory cell; a second word line connected to the second memory cell; and a control circuit. The control circuit is configured to, in a first read operation to read a first bit stored in the first memory cell, apply a first voltage to the first word line, and then, apply a first read voltage lower than the first voltage, to the first word line, and apply a second voltage to the second word line, and then, apply a third voltage lower than the second voltage and higher than the first voltage, to the second word line. The third voltage is applied to the second word line after the first read voltage is applied to the first word line.

Abstract: A location of at least one fail bit to be repaired in a memory block of a memory is extracted from at least one memory test on the memory block. An available repair resource in the memory for repairing the memory block is obtained. It is checked, using machine learning, whether the at least one fail bit is unrepairable, according to the location of the at least one fail bit, and the available repair resource. When the checking indicates that the at least one fail bit is not unrepairable, it is determined whether a Constraint Satisfaction Problem (CSP) containing a plurality of constraints is solvable. The constraints correspond to the location of the at least one fail bit in the memory block, and the available repair resource. In response to determining that the CSP is not solvable, the memory block is marked as unrepairable or the memory is rejected.

Abstract: An apparatus is provided which comprises: a stack comprising a magnetic insulating material (MI such as EuS, EuO, YIG, TmIG, or GaMnAs) and a transition metal dichalcogenide (TMD such as MoS2, MoSe2, WS2, WSe2, PtS2, PtSe2, WTe2, MoTe2, or graphene), wherein the magnetic insulating material has a first magnetization; a magnet with a second magnetization, wherein the magnet is adjacent to the TMD of the stack; and an interconnect comprising a spin orbit material, wherein the interconnect is adjacent to the magnet.

Abstract: An apparatus and method for designing memory macro blocks. A memory includes one or more memory banks, each with one or more arrays and input/output (I/O) blocks used to perform read accesses and write accesses. An array that utilizes multiple memory bit cells, and the I/O blocks are placed in a manner that they are abutting one another. The layout of the memory bit cells and the I/O blocks use a same subset of parameters of a semiconductor fabrication process. As a result, the memory bank does not include the placement of any boundary cells, which are used to improve yield of semiconductor layout. By skipping the use of the boundary cells, the dimensions of the memory bank are reduced, and layout density increases. Additionally, the memory bit cells use one or more p-type devices for one or more read pass gates.

Abstract: Systems and methods for precision writing of weight values to a memory capable of storing multiple levels in each cell are disclosed. Embodiments include logic to compare an electrical parameter read from a memory cell with a base reference and an interval reference, and stop writing once the electrical parameter is between the base reference and the base plus the interval reference. The interval may be determined using a greater number of levels than the number of stored levels, to prevent possible overlap of read values of the electrical parameter due to memory device variations.

Abstract: A memory device is provided. The memory device includes: a memory cell array including a plurality of rows; and a refresh control circuit including a plurality of registers each configured to store a row address. The refresh control circuit is configured to: determine, based on an incoming row address satisfying a replacement condition, in a first determination, whether to replace a first row address stored in a first register among the plurality of registers with the incoming row address based on a replacement probability; maintain the first row address stored in the first register or replace the first row address stored in the first register with the incoming row address based on a first result of the first determination; and determine, in a second determination, a victim row address to be refreshed based on a second row address stored in a second register among the plurality of registers.

Abstract: Embodiments of the disclosure, there is provided a method, a system for adjusting the memory, and a semiconductor device. The method for adjusting the memory includes: acquiring a mapping relationship between a temperature of a transistor, an equivalent width-length ratio of a sense amplifier transistor in a sense amplifier and an actual time at which the data is written into the memory; acquiring a current temperature of the transistor; and adjusting the equivalent width-length ratio, based on the current temperature and the mapping relationship, so that the actual time at which the data is written into the memory corresponding to the adjusted equivalent width-length ratio is within a preset writing time.

Abstract: The disclosed method may include detecting, by a control circuit coupled to a first read only memory (ROM) device and a second ROM device, a failure of a first output signal from the first ROM device to a common output. The first ROM device is connected to the common output and the second ROM device is disconnected from the common output. The method also includes switching, by the control circuit in response to detecting the failure, the common output from the first ROM device to the second ROM device. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: The present disclosure provides a memory device. The memory device includes a substrate, a dielectric layer, a first metallization layer, a first channel layer, a second metallization layer, and a second channel layer. The dielectric layer is disposed on the substrate. The first metallization layer is disposed within the dielectric layer and extends along a first direction. The first channel layer is surrounded by the first metallization layer. The second metallization layer is disposed within the dielectric layer and extends along the first direction. The second channel layer is surrounded by the second metallization layer. The first metallization layer includes a first protruding portion protruding toward the second metallization layer.

Abstract: An n+ layer 3a connected to a source line SL at both ends, an n+ layer 3b connected to a bit line BL, a first gate insulating layer 4a formed on a semiconductor substrate 1 existing on an insulating film 2, a gate conductor layer 16a connected to a plate line PL, a gate insulating layer 4b formed on the semiconductor substrate, and a second gate conductor layer 5b connected to a word line WL and having a work function different from a work function of the gate conductor layer 16a are disposed on the semiconductor substrate, and data hold operation of holding, near a gate insulating film, holes generated by an impact ionization phenomenon or gate-induced drain leakage current inside a channel region 12 of the semiconductor substrate 1 and data erase operation of removing the holes from inside the substrate 1 and the channel region 12 are performed by controlling voltage applied to the source line SL, the plate line PL, the word line WL, and the bit line BL.

Abstract: The present technology may include a first storage circuit connected to a plurality of memory banks, an error correction circuit, a read path including a plurality of sub-read paths connected between the plurality of memory banks and the error correction circuit, and a control circuit configured to control data output from the plurality of memory banks to be simultaneously stored in the first storage circuit by deactivating the read path during a first sub-test section, and to control the data stored in the first storage circuit to be sequentially transmitted to the error correction circuit by sequentially activating the plurality of sub-read paths during a second sub-test section.

Abstract: Systems and methods for repairing a memory. A method includes performing a repair analysis of the embedded memories to produce repair information. The method includes storing the repair information in the registers, where the registers are organized into groups having chains of identical length. The method includes performing collision detection between the repair information in each of the groups. The method includes merging the repair information in each of the groups. The method includes repairing the embedded memories using the merged repair information.

Abstract: According to various embodiments, a semiconductor memory device includes a substrate that includes a memory cell region and a test region. The semiconductor memory device further includes an active pattern on the memory cell region, a source/drain pattern on the active pattern, a dummy pattern on the test region, a first gate electrode on the dummy pattern, a first common contact, and a first wiring layer. The first wiring layer includes a first test line electrically connected to the first common contact. The first common contact includes a first contact pattern in contact with the dummy pattern, and a first gate contact connected to the first gate electrode. The first gate contact includes a body and a protrusion part. A lowermost level of a top surface of the active pattern is lower than a lowermost level of a top surface of the dummy pattern.

Abstract: Systems formed by a multi-bit three-transistor (3T) memory cell (i.e., dynamic-analog RAM) are provided. The 3T memory cell includes: a read-access transistor M1 in electrical communication with a read bitline; a switch transistor M2 in electrical communication with the read-access transistor M1; a write-access transistor M3 in electrical communication with the read-access transistor M1 and a write bitline; and a memory node MEM in electrical communication between the read-access transistor M1 and the write-access transistor M3, wherein the memory node MEM is configured to store a 4-bit weight WE. An array of the 3T memory cells (i.e., dynamic-analog RAMs) may form a computing-in-memory (CIM) macro, and further form a convolutional neural network (CNN) accelerator by communicating with an application-specific integrated circuit (ASIC) which communicates with a global weight static random access memory and an activation static random access memory.