Abstract: In an embodiment, a device includes: a package component including: integrated circuit dies; an encapsulant around the integrated circuit dies; a redistribution structure over the encapsulant and the integrated circuit dies, the redistribution structure being electrically coupled to the integrated circuit dies; sockets over the redistribution structure, the sockets being electrically coupled to the redistribution structure; and a support ring over the redistribution structure and surrounding the sockets, the support ring being disposed along outermost edges of the redistribution structure, the support ring at least partially laterally overlapping the redistribution structure.

Abstract: A device includes a semiconductor fin, and a gate stack on sidewalls and a top surface of the semiconductor fin. The gate stack includes a high-k dielectric layer, a work-function layer overlapping a bottom portion of the high-k dielectric layer, and a blocking layer overlapping a second bottom portion of the work-function layer. A low-resistance metal layer overlaps and contacts the work-function layer and the blocking layer. The low-resistance metal layer has a resistivity value lower than second resistivity values of both of the work-function layer and the blocking layer. A gate spacer contacts a sidewall of the gate stack.

Abstract: A TCAM comprises a plurality of first search lines, a plurality of second search lines, a plurality of memory cell strings and one or more current sensing units. The memory cell strings comprise a plurality of memory cells. The current sensing units are coupled to the memory cell strings. In a search operation, a determination that whether any of the data stored in the memory cell strings matches a data string to be searched is made according to whether the one or more current sensing units detect current from the memory cell strings, or according to the magnitude of the current flowing out from the memory cell strings detected by the one or more current sensing units. Each memory cell includes a first transistor, a second transistor and an inverter. The first search line is coupled to the second search line by the inverter.

Abstract: The disclosed system and method reduce on-chip power IR drop caused by large write current, to increase the write IO number or improve write throughput and to suppress write voltage ripple at the start and end of a write operation. The disclosed systems and methods are described in relation to stabilizing the bit line voltage for MRAMs, however, the disclosed systems and methods can be used to stabilize the bit line voltage of any memory configuration that draws large currents during short write pulses or, more generally, to selectively assist a power supply generator in supplying adequate power to a load at times of large power consumption.

Abstract: A reference circuit for generating a reference current includes a plurality of resistive elements including at least one magnetic tunnel junction (MTJ). A control circuit is coupled to a first terminal of the at least one MTJ and is configured to selectively flow current through the at least one MTJ in the forward and inverse direction to generate a reference current.

Abstract: A method includes forming a first conductive feature, depositing a passivation layer on a sidewall and a top surface of the first conductive feature, etching the passivation layer to reveal the first conductive feature, and recessing a first top surface of the passivation layer to form a step. The step comprises a second top surface of the passivation layer. The method further includes forming a planarization layer on the passivation layer, and forming a second conductive feature extending into the passivation layer to contact the first conductive feature.

Abstract: A multilevel content addressable memory, a multilevel coding method and a multilevel searching method are provided. The multilevel coding method includes the following steps. A highest decimal value of a multilevel-bit binary data is obtained. A length of a digital string data is set as being the highest decimal value of the multilevel-bit binary data. The multilevel-bit binary data is converted into the digital string data. If a content of the multilevel-bit binary data is an exact value, a number of an indicating bit in the digital string data is the exact value.

Abstract: An image sensor structure includes a semiconductor substrate, a plurality of image sensing elements, a reflective element, and a high-k dielectric structure. The image sensing elements are in the semiconductor substrate. The reflective element is in the semiconductor substrate and between the image sensing elements. The high-k dielectric structure is between the reflective element and the image sensing elements.

Abstract: A memory device and a method for manufacturing the memory device are provided. The memory device includes a stack and a plurality of memory strings. The stack is disposed on the substrate, and the stack includes a plurality of conductive layers and a plurality of insulating layers alternately stacked. The memory strings pass through the stack along a first direction, wherein a first memory string in the memory strings includes a first conductive pillar and a second conductive pillar, a channel layer, and a memory structure. The first conductive pillar and the second conductive pillar respectively extend along the first direction and are separated from each other. The channel layer is disposed between the first conductive pillar and the second conductive pillar. The memory structure surrounds the second conductive pillar, and the memory structure includes a resistive memory material.

Abstract: A semiconductor device includes a source/drain feature over a semiconductor substrate, channel layers over the semiconductor substrate and connected to the source/drain feature, a gate portion between vertically adjacent channel layers, and an inner spacer between the source/drain feature and the gate portion and between adjacent channel layers. The semiconductor device further includes an air gap between the inner spacer and the source/drain feature.

Abstract: A TCAM comprises a plurality of first search lines, a plurality of second search lines, a plurality of memory cell strings and one or more current sensing units. The memory cell strings comprise a plurality of memory cells. The current sensing units are coupled to the memory cell strings. In a search operation, a determination that whether any of the data stored in the memory cell strings matches a data string to be searched is made according to whether the one or more current sensing units detect current from the memory cell strings, or according to the magnitude of the current flowing out from the memory cell strings detected by the one or more current sensing units. Each memory cell includes a first transistor and a second transistor. Gates of the first and second transistors are coupled to a corresponding first search line and a corresponding second search line.

Abstract: A device includes a semiconductor fin, and a gate stack on sidewalls and a top surface of the semiconductor fin. The gate stack includes a high-k dielectric layer, a work-function layer overlapping a bottom portion of the high-k dielectric layer, and a blocking layer overlapping a second bottom portion of the work-function layer. A low-resistance metal layer overlaps and contacts the work-function layer and the blocking layer. The low-resistance metal layer has a resistivity value lower than second resistivity values of both of the work-function layer and the blocking layer. A gate spacer contacts a sidewall of the gate stack.

Abstract: A semiconductor device and a method of operating the semiconductor device are disclosed. In one aspect, the semiconductor device includes a plurality of memory cells, a first reference cell connected to a first subset of the plurality of memory cells via a first common source line, and a second reference cell connected to a second subset of the plurality of memory storage cells via a second common source line. The semiconductor device also includes a sense amplifier configured to, when reading from a first memory cell of the first subset, receive an output from the second reference cell and an output from the first memory cell.

Abstract: A circuit includes a first transistor and a second transistor cross-coupled with each other such that a source of the first transistor and a source of the second transistor are connected to a power supply, a gate of the first transistor is connected to a drain of the second transistor at a first node, a gate of the second transistor is connected to a drain of the first transistor at a second node. The circuit can provide a first level of a word line voltage to the memory cell by directly coupling the power supply configured at a first level to the memory cell through the second transistor and a third transistor, and provide a second level of the word line voltage by directly coupling the power supply configured at a second level to the memory cell through the second transistor and the third transistor.

Abstract: Compute-in memory (CIM) devices are provided. A memory is configured to multiply input data by a weight to obtain an adder input. An addition circuit is configured to receive the adder input to provide an adder output, and includes a pre-computation circuit and an adder tree. The pre-computation circuit includes a parameter extractor and a parameter identification circuit. The parameter extractor is configured to extract an input parameter from the adder input. The parameter identification circuit is configured to provide a pre-computation result corresponding to the input parameter as the adder output when determining that the input parameter is present in a parameter table, and provide a control signal when determining that the input parameter is not present in the parameter table. The adder tree is configured to provide the adder output according to the adder input in response to the control signal.

Abstract: A circuit includes a first transistor and a second transistor cross-coupled with each other such that a source of the first transistor and a source of the second transistor are connected to a power supply, a gate of the first transistor is connected to a drain of the second transistor at a first node, a gate of the second transistor is connected to a drain of the first transistor at a second node. The circuit can provide a first level of a word line voltage to the memory cell by directly coupling the power supply configured at a first level to the memory cell through the second transistor and a third transistor, and provide a second level of the word line voltage by directly coupling the power supply configured at a second level to the memory cell through the second transistor and the third transistor.

Abstract: A memory device includes a plurality of magnetoresistive random-access memory (MRAM) cells including a first one-time programmable (OTP) MRAM cell. A first OTP select transistor is connected to the first OTP MRAM cell. The first OTP select transistor configured to selectively apply a breakdown current to the first OTP MRAM cell to write the first OTP MRAM cell to a breakdown state.

Abstract: A memory device includes a computing-in-memory macro and a clock generating circuit. The computing-in-memory macro is configured to perform in-memory computing based on a first clock signal. The clock generating circuit is arranged within the computing-in-memory macro and configured to generate the first clock signal. A frequency of the first clock signal is modified according to a condition of the computing-in-memory macro to cause the first clock signal to conform to an operation speed of the in-memory computing.

Abstract: A memory device includes a plurality of magnetoresistive random-access memory (MRAM) cells including a first one-time programmable (OTP) MRAM cell. A first OTP select transistor is connected to the first OTP MRAM cell. The first OTP select transistor configured to selectively apply a breakdown current to the first OTP MRAM cell to write the first OTP MRAM cell to a breakdown state.

Abstract: A multiply-accumulate (MAC) device for compute-in-memory (CIM) includes an input driver configured to provide a plurality of input signals including a first input signal and a second input signal. A lookup table (LUT) stores or accesses a plurality of CIM weight signals including a first CIM weight signal and a second CIM weight signal. The LUT is configured to receive the first input signal and the second input signal and provide a sum output based on the first and second input signals and the first and second CIM weight signals.