A layout structure of a capacitive cell using forksheet FETs is provided. In transistors P3 and N3, VDD is supplied to a pair of pads and a gate interconnect, and VSS is supplied to a pair of pads and a gate interconnect. Capacitances are produced between nanosheets and the gate interconnect and between nanosheets and the gate interconnect. The faces of the nanosheets closer to the nanosheets are exposed from the gate interconnect, and the faces of the nanosheets closer to the nanosheets are exposed from the gate interconnect.

Integrated circuit (“IC”) layouts are disclosed for improving performance of memory arrays, such as static random access memory (“SRAM”). An exemplary IC device includes an SRAM cell and an interconnect structure electrically coupled to the SRAM cell. The interconnect structure includes a first metal layer electrically coupled to the SRAM cell that includes a bit line, a first voltage line having a first voltage, a word line landing pad, and a second voltage line having a second voltage that is different than the first voltage. The first voltage line is adjacent the bit line. The word line landing pad is adjacent the first voltage line. The second voltage line is adjacent the word line landing pad. A second metal layer is disposed over the first metal layer. The second metal layer includes a word line that is electrically coupled to the word line landing pad.

Vertical integration schemes and circuit elements architectures for area scaling of semiconductor devices are described. In an example, an inverter structure includes a semiconductor fin separated vertically into an upper region and a lower region. A first plurality of gate structures is included for controlling the upper region of the semiconductor fin. A second plurality of gate structures is included for controlling the lower region of the semiconductor fin. The second plurality of gate structures has a conductivity type opposite the conductivity type of the first plurality of gate structures.

Described is a packaging technology to improve performance of an AI processing system. An IC package is provided which comprises: a substrate; a first die on the substrate, and a second die stacked over the first die. The first die includes memory and the second die includes computational logic. The first die comprises a ferroelectric RAM (FeRAM) having bit-cells. Each bit-cell comprises an access transistor and a capacitor including ferroelectric material. The access transistor is coupled to the ferroelectric material. The FeRAM can be FeDRAM or FeSRAM. The memory of the first die may store input data and weight factors. The computational logic of the second die is coupled to the memory of the first die. The second die is an inference die that applies fixed weights for a trained model to an input data to generate an output. In one example, the second die is a training die that enables learning of the weights.

A semiconductor structure includes a substrate having a frontside and a backside; a static random-access memory (SRAM) circuit having SRAM bit cells formed on the frontside of the substrate, wherein each of the SRAM bit cells including two inverters cross-coupled together, and a first and second pass gates coupled to the two inverters; a first bit-line disposed on the frontside of the substrate and connected to the first pass gate; and a second bit-line disposed on the backside of the substrate and connected to the second pass gate.

An integrated circuit (IC) that includes a memory cell having a first p-type active region, a first n-type active region, a second n-type active region, and a second p-type active region. Each of the first and the second p-type active regions includes a first group of vertically stacked channel layers having a width W1, and each of the first and the second n-type active regions includes a second group of vertically stacked channel layers having a width W2, where W2 is less than W1. The IC structure further includes a standard logic cell having a third n-type fin and a third p-type fin. The third n-type fin includes a third group of vertically stacked channel layers having a width W3, and the third p-type fin includes a fourth group of vertically stacked channel layers having a width W4, where W3 is greater than or equal to W4.

A transistor includes a gate structure that has a first gate dielectric layer and a second gate dielectric layer. The first gate dielectric layer is disposed over the substrate. The first gate dielectric layer contains a first type of dielectric material that has a first dielectric constant. The second gate dielectric layer is disposed over the first gate dielectric layer. The second gate dielectric layer contains a second type of dielectric material that has a second dielectric constant. The second dielectric constant is greater than the first dielectric constant. The first dielectric constant and the second dielectric constant are each greater than a dielectric constant of silicon oxide.

A semiconductor device includes a first memory column group including a plurality of memory columns in which a plurality of bit cells are disposed; and a first peripheral column group including a plurality of peripheral columns in which a plurality of standard cells are disposed, wherein the plurality of standard cells are configured to perform an operation of reading/writing data from/to the plurality of bit cells through a plurality of bit lines, wherein the first memory column group and the first peripheral column group correspond to each other in a column direction, and wherein at least one of the plurality of peripheral columns has a cell height different from cell heights of the other peripheral columns, the cell height being measured in a row direction in which a gate line is extended.

A 3D semiconductor device, the device including: a first level including a first single crystal layer, the first level including a plurality of first transistors and at least one metal layer, where the at least one metal layer overlays the first single crystal layer, and where the at least one metal layer includes interconnects between the plurality of first transistors, the interconnects between the plurality of first transistors include forming first control circuits; a second level overlaying the at least one metal layer, the second level including a plurality of second transistors; a third level overlaying the second level, the third level including a plurality of third transistors, where the second level includes a plurality of first memory cells, the first memory cells each including at least one of the plurality of second transistors, where the third level includes a plurality of second memory cells, the second memory cells each including at least one of the plurality of third transistors, where at least one of the plurality of second memory cells is at least partially atop of the first control circuits, where the first control circuits are adapted to control data written to at least one of the plurality of second memory cells; and where the plurality of second transistors are horizontally oriented transistors.

An N-type metal oxide semiconductor (NMOS) transistor includes a first gate and a first spacer structure disposed on a first sidewall of the first gate in a first direction. The first spacer structure has a first thickness in the first direction and measured from an outermost point of an outer surface of the first spacer structure to the first sidewall. A P-type metal oxide semiconductor (PMOS) transistor includes a second gate and a second spacer structure disposed on a second sidewall of the second gate in the first direction and measured from an outermost point of an outer surface of the second spacer structure to the second sidewall. The second spacer structure has a second thickness that is greater than the first thickness. The NMOS transistor is a pass-gate of a static random access memory (SRAM) cell, and the PMOS transistor is a pull-up of the SRAM cell.