Techniques for performing analog-to-digital conversion are disclosed. For example, a method performs an analog-to-digital conversion of an analog input to a digital output comprising a set of bits, the set of bits comprising a most significant bit and one or more additional bits, the analog-to-digital conversion starting at a given one of the one or more additional bits following the most significant bit.

In a compute-in-memory (“CIM”) system, current signals, indicative of the result of a multiply-and-accumulate operation, from a CIM memory circuit are computed by comparing them with reference currents, which are generated by a current digital-to-analog converter (“DAC”) circuit. The memory circuit can include non-volatile memory (“NVM”) elements, which can be multi-level or two-level NVM elements. The characteristic sizes of the memory elements can be binary weighted to correspond to the respective place values in a multi-bit weight and/or a multi-bit input signal. Alternatively, NVM elements of equal size can be used to drive transistors of binary weighted sizes. The current comparison operation can be carried out at higher speeds than voltage computation. In some embodiments, simple clock-gated switches are used to produce even currents in the current summing branches. The clock-gated switches also serve to limit the time the cell currents are on, thereby reducing static power consumption.

An analog-to-digital converter (ADC) is provided. In some examples, the ADC includes a first reference voltage supply input, a second reference voltage supply input, a comparator comprising an input node, and a first reference switch coupled between the second reference voltage supply input and the input node of the comparator. The ADC also includes a set of capacitors, where each capacitor of the set of capacitors comprises a first terminal. In addition, the ADC includes a second reference switch coupled between the first reference voltage supply input and the first terminal of each capacitor of the set of capacitors. The ADC further includes a third switch coupled between the input node of the comparator and the first terminal of each capacitor of the set of capacitors.

A class D amplifier including a pulse width modulation (PWM) control loop, an H-bridge driver, a PWM controller having a PWM pulse generator to generate PWM pulses supplied to the H-bridge driver in response to an ADC value output by an analog-to-digital converter of the PWM control loop, and a comparator. The comparator is configured to trigger a cutoff of a PWM pulse generated by the PWM pulse generator during a respective loop cycle of the PWM control loop and to trigger generation of at least one counter PWM pulse with an opposite polarity in the respective loop cycle such that a net pulse energy of the cutoff PWM pulse and of the at least one generated counter PWM pulse corresponds to a pulse energy representing the ADC value provided by the analog-to-digital converter of the PWM control loop during the respective loop cycle.

Analogue-to-digital converter, ADC, circuitry, including: an analogue input terminal; a comparator having first and second comparator-input terminals; and successive-approximation control circuitry to apply a potential difference across the first and second comparator-input terminals based on an input voltage signal, and to control the potential difference for a series of successive approximation operations to cause the comparator to test in each successive approximation operation whether a magnitude of an analogue input voltage signal is larger or smaller than a corresponding test value, the test value for each successive approximation operation being, dependent on a comparison result generated by the comparator in the preceding approximation operation, bigger or smaller than the test value for the preceding approximation operation by a difference amount configured for that successive approximation operation.

A mixed-signal in-memory computing sub-cell only requires 9 transistors for 1-bit multiplication. A computing cell is constructed from a plurality of such sub-cells that share a common computing capacitor and a common transistor. Also proposed is a MAC array for performing MAC operations, which includes a plurality of the computing cells each activating the sub-cells therein in a time-multiplexed manner. Also proposed is a differential version of the MAC array with improved computation error tolerance and an in-memory mixed-signal computing module for digitalizing parallel analog outputs of the MAC array and for performing other tasks in the digital domain. An ADC block in the computing module makes full use of capacitors in the MAC array, thus allowing the computing module to have a reduced area and suffer from less computation errors. Also proposed is a method of fully taking advantage of data sparsity to lower the ADC block's power consumption.

A circuit system for weight modulation and image recognition of a memristor array includes a personal computer (PC), a field-programmable gate array (FPGA) chip, a digital-to-analog conversion unit, a switch unit, a memristor array unit, an integration and signal amplification circuit, and an analog-to-digital converter. The circuit system selects a to-be-realized function such as array reading and writing, weight modulation or image recognition, converts a command or an RGB value of an image collected by the PC into a corresponding grayscale value, and sends the grayscale value to the FPGA chip. The FPGA chip controls and selects a to-be-modulated memristor array unit through the digital-to-analog conversion unit and the switch unit. An application program of the PC controls the FPGA chip in real time to realize array reading and writing, weight modulation, and image recognition, and then the FPGA chip displays a result on the PC in real time.

A device for buffering a reference signal comprises a regulator circuit configured to generate at least two replicas of the reference signal as regulated output signals. The device further comprises a receiving circuit configured to receive the regulated output signals in a switchable manner. In this context, the regulated output signals are configured to have different performance characteristics.

A dual-loop analog to digital converter (ADC) includes an asynchronous inner loop including first and second comparators and a state machine, where outputs of the first and second comparators are coupled to inputs of the state machine, and where outputs of the state machine are cross-coupled to enable ports of the first and second comparators. The ADC includes a synchronous outer loop including a successive approximation register (SAR), a digital to analog converter (DAC), and the first and second comparators, where the outputs of the first and second comparators are coupled to inputs of the SAR, an N-bit output of the SAR is coupled to an N-bit input of the DAC, and a differential output of the DAC is coupled to inputs of the first and second comparators, where a state of the state machine is independent of the state of the SAR.

A method of operating an analog-to-digital converter includes in a first sampling stage, switching a swap signal to a first level for a first selection circuit to reset a first capacitor array according to a first voltage configuration and for a second selection circuit to reset a second capacitor array according to the first voltage configuration, and in a second sampling stage, switching the swap signal to a second level for the first selection circuit to reset the first capacitor array according to the second voltage configuration and for the second selection circuit to reset the second capacitor array according to the second voltage configuration. A control logic circuit is used to switch the swap signal between the first level and the second level in a uniform order in a plurality of sampling stages.