A flexible RAM loader including a shift register that includes a first data section coupled with a serial data input, and a second data section selectively coupled with a first parallel data input. The shift register is configured to load data serially from the serial data input to the first data section and the second data section when the second data section is uncoupled from the first parallel data input, and, when the second data section is coupled with the first parallel data input, configured to load data in parallel from the serial data input into the first data section and from the first parallel data input into the second data section. The flexible RAM loader also including a test register comprising a selection bit to couple the second data section with the first parallel data input.

A memory device according to the present invention comprises: a memory cell array in which memory cells are connected to wordlines and bitlines in a matrix form; and a control circuit for programming the memory cells or controlling a read operation, according to a start address, a burst length, a latency length, and a program or read command which are transmitted from a host, wherein the control circuit may comprise: a pulse generation unit for generating register pulses and counter pulses in synchronization with an operation clock; and a counter that sets the start address in synchronization with the register pulses, counts the number of counter pulses corresponding to the sum of the latency length and the burst length, and increases an address from the start address to the sum of the start address and the burst length.

A semiconductor device of an embodiment includes a seed generator circuit configured to generate a seed from inputted data by using first random number sequence data generated by an XorShift circuit; and a random number generator circuit configured to receive the seed as input to generate second random number sequence data by a second XorShift circuit.

The present disclosure relates to circuits, systems, and methods of operation for a memory device. In an example, a memory device includes a memory array including a plurality of memory cells, each memory cell having an impedance that varies in accordance with a respective data value stored therein; and a tracking memory cell having an impedance based on a tracking data value stored therein; and a read circuit coupled to the memory array, the read circuit configured to determine an impedance of a selected memory cells with respect to the impedance of the tracking memory cell; read a data value stored within the selected memory cell based upon a voltage change of a signal node voltage corresponding to the impedance of the selected memory cell.

The present disclosure relates to circuits, systems, and methods of operation for a memory device. In an example, a memory device includes a memory array including a plurality of memory cells, each memory cell having an impedance that varies in accordance with a respective data value stored therein; and a tracking memory cell having an impedance based on a tracking data value stored therein; and a read circuit coupled to the memory array, the read circuit configured to determine an impedance of a selected memory cells with respect to the impedance of the tracking memory cell; read a data value stored within the selected memory cell based upon a voltage change of a signal node voltage corresponding to the impedance of the selected memory cell.

The present disclosure includes apparatuses and methods related to scatter/gather in a memory device. An example apparatus comprises a memory device that includes an array of memory cells, sensing circuitry, and a memory controller coupled to one another. The sensing circuitry includes a sense amplifier and a compute component configured to implement logical operations. A channel controller is configured to receive a block of instructions, the block of instructions including individual instructions for at least one of a gather operation and a scatter operation. The channel controller is configured to send individual instructions to the memory device and to control the memory controller such that the at least one of the gather operation and the scatter operation is executed on the memory device based on a corresponding one of the individual instructions.

A semiconductor memory device and a memory system are provided. The semiconductor memory device includes a fingerprint read signal generator configured to generate a fingerprint read signal in response to a refresh counting control signal, a memory cell array comprising a plurality of sub memory cell array blocks, a fingerprint output unit configured to receive data output from memory cells connected to one selected among a plurality of word lines and one selected among a plurality of bit lines of one among the plurality of sub memory cell array blocks in response to the fingerprint read signal to generate fingerprint data, and a pseudorandom number generator configured to perform a linear feedback shifting operation in response to an active command to generate sequence data, receive the fingerprint data in response to the fingerprint read signal, and generate the sequence data based on the fingerprint data.

A row hammer control method and a memory device are provided. The memory device monitors the row hammer address(es) having the number of accesses equal to or more than a predetermined number of times or having a higher number of accesses as compared with other access addresses during the first row hammer monitoring time frame and malicious row hammer address(es) accessed at random sampling time points during the second row hammer monitoring time frame and being the same as the row hammer address(es), notifies a memory controller of the malicious row hammer address(es) when the number of malicious row hammer addresses exceeds a threshold value, and causes a target refresh a memory cell row physically adjacent to a memory cell row corresponding to the malicious row hammer address(es) to be performed.

In some embodiments, an in-memory-computing SRAM macro based on capacitive-coupling computing (C3) (which is referred to herein as “C3SRAM”) is provided. In some embodiments, a C3SRAM macro can support array-level fully parallel computation, multi-bit outputs, and configurable multi-bit inputs. The macro can include circuits embedded in bitcells and peripherals to perform hardware acceleration for neural networks with binarized weights and activations in some embodiments. In some embodiments, the macro utilizes analog-mixed-signal capacitive-coupling computing to evaluate the main computations of binary neural networks, binary-multiply-and-accumulate operations. Without needing to access the stored weights by individual row, the macro can assert all of its rows simultaneously and form an analog voltage at the read bitline node through capacitive voltage division, in some embodiments. With one analog-to-digital converter (ADC) per column, the macro cab realize fully parallel vector-matrix multiplication in a single cycle in accordance with some embodiments.

The present disclosure includes apparatuses and methods related to scatter/gather in a memory device. An example apparatus comprises a memory device that includes an array of memory cells, sensing circuitry, and a memory controller coupled to one another. The sensing circuitry includes a sense amplifier and a compute component configured to implement logical operations. A channel controller is configured to receive a block of instructions, the block of instructions including individual instructions for at least one of a gather operation and a scatter operation. The channel controller is configured to send individual instructions to the memory device and to control the memory controller such that the at least one of the gather operation and the scatter operation is executed on the memory device based on a corresponding one of the individual instructions.