A dynamic comparator includes a differential amplifier stage, a switching unit and a switching charge storage unit. The switching charge storage unit includes a plurality of switching transistors, and a charge storage capacitor electrically connected to the plurality of switching transistors. When an operational mode of the dynamic comparator is switched from a comparison state to a reset state, a voltage on one of a first terminal and a second terminal of the charge storage capacitor is increased from a half of the system voltage to a system voltage, so as to implement a charge recycle effect. The dynamic comparator of the present invention can have lower power consumption and lower charge-discharge current.

A dynamic comparator includes a differential amplifier stage, a switching unit and a switching charge storage unit. The switching charge storage unit includes a plurality of switching transistors, and a charge storage capacitor electrically connected to the plurality of switching transistors. When an operational mode of the dynamic comparator is switched from a comparison state to a reset state, a voltage on one of a first terminal and a second terminal of the charge storage capacitor is increased from a half of the system voltage to a system voltage, so as to implement a charge recycle effect. The dynamic comparator of the present invention can have lower power consumption and lower charge-discharge current.

Digital-to-analog conversion circuit, digital-to-analog conversion method, display apparatus are disclosed. Digital-to-analog conversion circuit may comprise: voltage dividing sub-circuit comprising M voltage dividing signal terminals; decoding sub-circuit comprising M input and output terminals, M input terminals electrically coupled to first to M.sup.th voltage dividing signal terminals of voltage dividing sub-circuit respectively, decoding sub-circuit configured to receive digital signal and select one of M input terminals to be electrically connected with output terminal according to digital signal; amplification sub-circuit comprising input and output terminals, input terminal of amplification sub-circuit electrically coupled to output terminal of decoding sub-circuit, amplification sub-circuit configured to amplify signal at its input terminal, output analog gray-scale voltage at output terminal, voltage dividing signal at voltage dividing signal terminal is less than or equal to ½ of maximum load voltage at output terminal of digital-to-analog conversion circuit, amplification sub-circuit has amplification coefficient N greater than or equal to 2.

A touch processing circuit includes: a front-end circuit including an amplifier, a first capacitor, a second capacitor, a third capacitor, and a plurality of switches each having two ends that are selectively connected each other, the front-end circuit being configured to process an input signal varying according to a touch; and a controller controlling the plurality of switches so that the front-end circuit is configured as a first circuit that accumulates deviation of the input signal between a first phase and a second phase during an integration period and a second circuit that converts the accumulated deviation into a digital signal during a conversion period.

A multi-instance time-interleaving (TI) system and method of operation therefor. The system includes a plurality of TI devices, each with a plurality of clock generation units (CGUs) coupled to an interleaver network. Within each TI device, the plurality of CGUs provides a plurality of clock signals needed by the interleaver network. A phase detector device is coupled to the plurality of TI devices and configured to determine any phase differences between the clock signals of a designated reference TI device and the corresponding clock signals of each other TI device. To determine the phase differences, the phase detector can use a logic comparator configuration, a time-to-digital converter (TDC) configuration, or an auto-correlation configuration. The phases of the clock signals of each other TI device can be aligned to the reference TI device using internal phase control, retimers, delay cells, finite state machines, or the like.

A sensing circuit includes a first input selecting circuit connected to a first sensing line and a second sensing line, a first path setting circuit that sets a path of a first sensing signal received from the first sensing line or a path of a second sensing signal received from the second sensing line, a second path setting circuit that sets a path of a sensing reference voltage, a first switch matrix connected to the first path setting circuit and the second path setting circuit, a first mode setting circuit connected to a first output terminal of the first switch matrix, a first common sensing amplifier connected to the first mode setting circuit, a second mode setting circuit connected to a second output terminal of the first switch matrix, and a second common sensing amplifier connected to the second mode setting circuit.

A sensing circuit includes a first input selecting circuit connected to a first sensing line and a second sensing line, a first path setting circuit that sets a path of a first sensing signal received from the first sensing line or a path of a second sensing signal received from the second sensing line, a second path setting circuit that sets a path of a sensing reference voltage, a first switch matrix connected to the first path setting circuit and the second path setting circuit, a first mode setting circuit connected to a first output terminal of the first switch matrix, a first common sensing amplifier connected to the first mode setting circuit, a second mode setting circuit connected to a second output terminal of the first switch matrix, and a second common sensing amplifier connected to the second mode setting circuit.

A memory device and an operation method thereof are provided. The memory device includes: a memory array including a plurality of memory cells for storing a plurality of weights; a multiplication circuit for performing bitwise multiplication on a plurality of input data and the weights to generate a plurality of multiplication results, wherein in performing bitwise multiplication, the memory cells generate a plurality of memory cell currents; a digital accumulating circuit for performing a digital accumulating on the multiplication results; an analog accumulating circuit for performing an analog accumulating on the memory cell currents to generate a first MAC operation result; and a decision unit for deciding whether to perform the analog accumulating; the digital accumulating or a hybrid accumulating, wherein in performing the hybrid accumulating, whether the digital accumulating circuit is triggered is based on the first MAC operation result.

Method and apparatus for sharing an analog signal for use by a plurality of devices are disclosed. In some implementations, the analog signal may be generated by a controller. The controller also may generate a control signal to determine when other devices use the analog signal. In one implementation, the control signal may be a token that may be transmitted and received by the other devices. If a device possess the token, then the device may use the analog signal. If the device does not possess the token, then the device may not use the analog signal. In another implementation, the controller may transmit a peer-to-peer message to a selected device. When the selected device receives the peer-to-peer message, then the selected device may use the analog signal. In this manner, the controller ensures that only one device at a time may use the analog signal.

Apparatuses and methods can be related to implementing a Bayesian neural network in a memory. A Bayesian neural network can be implemented utilizing a resistive memory array. The memory array can comprise programmable memory cells that can be programed and used to store weights of the Bayesian neural network and perform operations consistent with the Bayesian neural network.