A multiplexer circuit includes first and second fins each extending in an X-axis direction. First, second, third and fourth gates extend in a Y-axis direction perpendicular to the X-axis direction and contact the first and second fins. The first, second, third and fourth gates are configured to receive first, second, third and fourth data signals, respectively. Fifth, sixth, seventh and eighth gates extend in the Y-axis direction and contact the first and second fins, the fifth, sixth, seventh and eighth gates, and are configured to receive the first, second, third and fourth select signals, respectively. An input logic circuit is configured to provide an output at an intermediate node. A ninth gate extends in the Y-axis direction and contacts the first and second fins. An output logic circuit is configured to provide a selected one of the first, second, third and fourth data signals at an output terminal.

A memory device includes a plurality of word lines elongated along a first direction, and at least one memory unit. The at least one memory unit includes a plurality of memory cells, at least one bit line, and at least one column word line. The plurality of memory cells are arranged along a second direction different from the first direction. The at least one bit line is elongated along the second direction, and configured to transmit data of a selected memory cell. The at least one column word line is elongated along the second direction, and configured to control electrical connections between the memory cells and the at least one bit line, wherein the selected memory cell is selected by a corresponding word line and the at least one column word line.

In some embodiments, a system comprises a static random access memory (SRAM) device and a controller. The SRAM device comprises a bit cell array comprising a plurality of bit cells arranged in a plurality of rows and a plurality of columns, each column operatively coupled to a pair of bit lines, wherein the plurality of columns is arranged as a plurality of column groups each comprising a plurality of local columns. The SRAM device further comprises a plurality of column decoders, each associated with a column group of the plurality of column groups. In some embodiments, the controller may be configured to read the local columns included in the column group by, for a given local column, sensing a voltage difference on a corresponding pair of bit lines, in a rearranged sequential order that is different from a physical sequential order of the plurality of local columns.

An integrated circuit that includes very large adder circuitry is provided. The very large adder circuitry receives more than two inputs each of which has hundreds or thousands of bits. The very large adder circuitry includes multiple adder nodes arranged in a tree-like network. The adder nodes divide the input operands into segments, computes the sum for each segment, and computes the carry for each segment independently from the segment sums. The carries at each level in the tree are accumulated using population counters. After the last node in the tree, the segment sums can then be combined with the carries to determine the final sum output. An adder tree network implemented in this way asymptotically approaches the area and performance latency as an adder network that uses infinite speed ripple carry adders.

An in-memory computing device includes a memory cell array and a column peripheral circuit including a plurality of column peripheral units connected to a plurality of pairs of bit lines connected to the memory cell array. Each of the column peripheral units includes a sense amplifying and writing unit sensing and amplifying bitwise data through one pair of bit lines among the pairs of bit lines and an arithmetic logic unit performing an arithmetic operation with a full adder Boolean equation based on the bitwise data and performing a write back operation on operation data obtained by the arithmetic operation via the sense amplifying and writing unit.

Embodiments include a memory device with an improved calibration circuit. Memory device input/output pins include delay lines for adjusting the delay in each memory input/output signal path. The delay adjustment circuitry includes digital delay lines for adjusting this delay. Further, each digital delay line is calibrated via a digital delay line locked loop which enables adjustment of the delay through the digital delay line in fractions of a unit interval across variations due to differences in manufacturing process, operating voltage, and operating temperature. The disclosed techniques calibrate the digital delay lines by measuring both the high phase and the low phase of the clock signal. As a result, the disclosed techniques compensate for duty cycle distortion by combining the calibration results from both phases of the clock signal. The disclosed techniques thereby result in lower calibration error relative to approaches that measure only one phase of the clock signal.

Various implementations described herein are directed to a device having a scan chain that receives a multi-bit input, provides a multi-bit output, and provides a multi-bit multiplexer output based on the multi-bit input and the multi-bit output. The device may have an error-bit generator that receives the multi-bit multiplexer output, receives a portion of the multi-bit input, receives a portion of the multi-bit output, and provides an error-bit output based on the multi-bit multiplexer output, the portion of the multi-bit input, and the portion of the multi-bit output.

A timing device includes an oven having a chamber, a crystal oscillator disposed in the chamber that generates a clock signal, and one or more sensors to generate operational characteristic signals indicative of respective operational characteristics of the crystal oscillator or the oven. The timing device includes a plurality of I/O connections and an IC device. The IC device includes processing logic to generate information that indicates how the generated clock signal is to be modified and a modulator coupled to the processing logic and the crystal oscillator. The modulator modulates the generated clock signal in relation to the information to generate a modulated clock signal indicative of the one or more operational characteristics of the crystal oscillator or the oven. The modulator outputs the modulated clock signal over a single one of the plurality of I/O connections.

Apparatus and methods for flexible input/output signaling over a same signaling channel are described. A programmable interface circuit includes a signaling channel that can be adapted, prior to use or during operation, for transmission and/or reception of different types of analog and digital signals. The interface circuit can be used for communications between an isolating communication controller and components of a machine that use diverse signaling types.

A chip package used as a logic drive, includes: multiple semiconductor chips, a polymer layer horizontally between the semiconductor chips; multiple metal layers over the semiconductor chips and polymer layer, wherein the metal layers are connected to the semiconductor chips and extend across edges of the semiconductor chips, wherein one of the metal layers has a thickness between 0.5 and 5 micrometers and a trace width between 0.5 and 5 micrometers; multiple dielectric layers each between neighboring two of the metal layers and over the semiconductor chips and polymer layer, wherein the dielectric layers extend across the edges of the semiconductor chips, wherein one of the dielectric layers has a thickness between 0.5 and 5 micrometers; and multiple metal bumps on a top one of the metal layers, wherein one of the semiconductor chips is a FPGA IC chip, and another one of the semiconductor chips is a NVMIC chip.