A memory device has a memory array including a memory segment to store weight data, a weight buffer coupled to the memory segment and configured to hold new weight data to be updated in the memory segment, a logic circuit, and a computation circuit coupled to an output of the logic circuit. The logic circuit further has a first input coupled to the memory segment by a bit line, and a second input configured to receive input data. The logic circuit is configured to generate, at the output, intermediate data corresponding to the input data and the weight data read from the memory segment through the bit line. The computation circuit is configured to, based on the intermediate data, generate output data corresponding to a computation performed on the input data and the weight data read from the at least one memory segment.

A semiconductor structure includes an array of two-port (TP) SRAM cells, each of which includes a write port and a read port. The write port includes two write pass gate (W_PG) transistors, two write pull-down (W_PD) transistors, and two write pull-up (W_PU) transistors. The array of TP SRAM cells includes first and second TP SRAM cells whose write ports abuts each other. Two W_PG transistors of the first and second TP SRAM cells share a common gate electrode. Source/drain electrodes of two W_PD transistors of the first and second TP SRAM cells share a common contact. The first TP SRAM cell includes a Vss conductor connected to the common contact. The second TP SRAM cell includes a write word line (W_WL) landing pad connected to the common gate electrode. The Vss conductor and the W_WL landing pad are located at a first metal layer.

An SRAM includes multiple memory cells, each memory cell includes a data storage unit; a data I/O control adapted to input data to, and output data from, a data line (BL); and multiple access controls respectively connected to at least two access control lines (WL's) and adapted to enable and disable the data input and output from the at least two WL's (WX and WY). The access controls are configured to permit data input only when both WL's are in their respective states that permit data input. A method of writing to a group of SRAM cells include sending a first write-enable signal to the cells via a first WL, sending a group of respective second write-enable signals to the respective cells, and, for each of the cells, preventing writing data to the cell if either of the first write-enable signal and respective second write enable signal is in a disable-state.

A compute-in-memory bitcell is provided that includes a pair of cross-coupled inverters for storing a stored bit. The compute-in-memory bitcell includes a logic gate for multiplying the stored bit with an input vector bit. An output node for the logic gate connects to a second plate of a capacitor. A first plate of the capacitor connects to a read bit line. A write driver controls a power supply voltage to the cross-coupled inverters, the first switch, and the second switch to capacitively write the stored bit to the pair of cross-coupled inverters.

Hot carrier injection (HCI) may be used to provide various improvements for one-time programmable (OTP) read-only memory (ROM) or physical unclonable function (PUF) circuits. HCI may be used to write a memory bit (e.g., logical 0 or 1), which may be used in OTP ROM. HCI may be used to provide improved programmable ROM (PROM) memory devices, such as to facilitate programming or to increase sensing window. HCI may also be used to write a memory bit in a PUF circuit. HCI may provide a cross-foundry portable PUF circuit that has an associated adjustable bit error rate (BER), which may be used to secure root key generation, or may be used to provide a unique identification (ID) for fuse replacement.

A dual-port static random access memory (SRAM) cell is provided. The dual-port SRAM cell includes: P-type active patterns that are spaced apart from one another along a first direction, each of the P-type active patterns extending in a second direction perpendicular to the first direction and including at least one transistor. The P-type active patterns include first through sixth P-type active patterns which are sequentially arranged along the first direction. A first cutting area is provided between the second P-type active pattern and a first boundary of the dual-port SRAM cell that extends along the first direction, and a second cutting area is provided between the fifth P-type active pattern and a second boundary that is opposite to the first boundary and extends along the first direction.

A dual-port static random access memory (SRAM) cell is provided. The dual-port SRAM cell includes: P-type active patterns that are spaced apart from one another along a first direction, each of the P-type active patterns extending in a second direction perpendicular to the first direction and including at least one transistor. The P-type active patterns include first through sixth P-type active patterns which are sequentially arranged along the first direction. A first cutting area is provided between the second P-type active pattern and a first boundary of the dual-port SRAM cell that extends along the first direction, and a second cutting area is provided between the fifth P-type active pattern and a second boundary that is opposite to the first boundary and extends along the first direction.

Systems and methods are provided for reducing power in in-memory computing, matrix-vector computations, and neural networks. An apparatus for in-memory computing using charge-domain circuit operation includes transistors configured as memory bit cells, transistors configured to perform in-memory computing using the memory bit cells, capacitors configured to store a result of in-memory computing from the memory bit cells, and switches, wherein, based on a setting of each of the switches, the charges on at least a portion of the plurality of capacitors are shorted together. Shorting together the plurality of capacitors yields a computation result.

A 3D semiconductor device with a built-in-test-circuit (BIST), the device comprising: a first single-crystal substrate with a plurality of logic circuits disposed therein, wherein said first single-crystal substrate comprises a device area, wherein said plurality of logic circuits comprise at least a first interconnected array of processor logic, wherein said plurality of logic circuits comprise at least a second interconnected set of circuits comprising a first logic circuit, a second logic circuit, and a third logic circuit, wherein said second interconnected set of logic circuits further comprise switching circuits that support replacing said first logic circuit and/or said second logic circuit with said third logic circuit; and said built-in-test-circuit (BIST), wherein said first logic circuit is testable by said built-in-test-circuit (BIST), and wherein said second logic circuit is testable by said built-in-test-circuit (BIST).

A 3D semiconductor device with a built-in-test-circuit (BIST), the device comprising: a first single-crystal substrate with a plurality of logic circuits disposed therein, wherein said first single-crystal substrate comprises a device area, wherein said plurality of logic circuits comprise at least a first interconnected array of processor logic, wherein said plurality of logic circuits comprise at least a second interconnected set of circuits comprising a first logic circuit, a second logic circuit, and a third logic circuit, wherein said second interconnected set of logic circuits further comprise switching circuits that support replacing said first logic circuit and/or said second logic circuit with said third logic circuit; and said built-in-test-circuit (BIST), wherein said first logic circuit is testable by said built-in-test-circuit (BIST), and wherein said second logic circuit is testable by said built-in-test-circuit (BIST).