An auto calibration method used in switching converters with constant on-time control. The auto calibration method includes: generating a periodical clock signal with a predetermined duty cycle; providing a first voltage and a second voltage to an on-time control circuit to generate an on-time control signal based on the first and second voltage; providing the clock signal and on-time control signal to a logic circuit to generate a switch control signal based on the clock signal and on-time control signal; comparing the duty cycle of the switch control signal with the duty cycle of the clock signal to adjust a calibration code signal; and adjusting circuit parameters of the on-time control circuit in accordance with the calibration code signal.

An analog-to-digital converter, including a sample/hold circuit; a reference voltage driver; a digital-to-analog converter; a comparator; and a logic circuit, wherein the reference voltage driver includes: a first voltage supplier circuit configured to output an external supply voltage provided from outside of the analog-to-digital converter; a second voltage supplier circuit configured to output a sampled reference voltage that is obtained during a sampling phase based on control signals received from the logic circuit; and a switching driver configured to electrically connect the first voltage supplier circuit to the digital-to-analog converter during a first conversion phase after the sampling phase based on the control signals received from the logic circuit, and to electrically connect the second voltage supplier circuit to the digital-to-analog converter during a second conversion phase based on the control signals received from the logic circuit.

An analog-to-digital converter, including a sample/hold circuit; a reference voltage driver; a digital-to-analog converter; a comparator; and a logic circuit, wherein the reference voltage driver includes: a first voltage supplier circuit configured to output an external supply voltage provided from outside of the analog-to-digital converter; a second voltage supplier circuit configured to output a sampled reference voltage that is obtained during a sampling phase based on control signals received from the logic circuit; and a switching driver configured to electrically connect the first voltage supplier circuit to the digital-to-analog converter during a first conversion phase after the sampling phase based on the control signals received from the logic circuit, and to electrically connect the second voltage supplier circuit to the digital-to-analog converter during a second conversion phase based on the control signals received from the logic circuit.

An analog-to-digital converter includes a switch circuit, a first capacitor array, a second capacitor array and a comparator. A method of operating the analog-to-digital converter includes switching a swap signal to a first level in a first sampling period for the switch circuit to couple the first capacitor array to a first input terminal of the comparator and a first signal source, and couple the second capacitor array to a second input terminal of the comparator and a second signal source, and switching the swap signal to a second level in a second sampling period for the switch circuit to couple the first capacitor array to the second input terminal of the comparator and the second signal source, and couple the second capacitor array to the first input terminal of the comparator and the first signal source.

A method of operating an analog-to-digital converter includes in a first conversion period, a comparator generating a first comparison result, a first selection circuit switching a voltage output to a first capacitor of a set of larger capacitor of a first capacitor array, and a second selection circuit switching a voltage output to a second capacitor of a set of larger capacitor of a second capacitor array, and in a second conversion period after the first conversion period, the comparator generating a second comparison result different from the first comparison result, the first selection circuit switching back the voltage output to a first capacitor portion of the first capacitor of the set of larger capacitor of the first capacitor array, and the second selection circuit switching back the voltage output to a first capacitor portion of the second capacitor of the set of larger capacitor of the second capacitor array.

An architecture for a multiplier-accumulator (MAC) uses a common Unit Element (UE) for each aspect of operation, the MAC formed as a plurality of MAC UEs, a plurality of Bias UEs, and a plurality of Analog to Digital Conversion (ADC) UEs which collectively perform a scalable MAC operation and generate a binary result. Each MAC UE, BIAS UE and ADC UE comprises groups of NAND gates with complementary outputs arranged in NAND-groups, each NAND gate coupled to a differential charge transfer bus through a binary weighted charge transfer capacitor to form an analog multiplication product as a charge applied to the differential charge transfer bus. The analog charge transfer bus is coupled to groups of ADC UEs with an ADC controller which enables and disables the ADC UEs using successive approximation to determine the accumulated multiplication result.

An architecture for a chopper stabilized multiplier-accumulator (MAC) uses a chop clock and common Unit Element (UE), the MAC formed as a plurality of MAC UEs receiving X and W values and a sign bit exclusive ORed with the chop clock, a plurality of Bias UEs receiving E value and a sign bit exclusive ORed with the chop clock, and a plurality of Analog to Digital Conversion (ADC) UEs which collectively perform a scalable MAC operation and generate a binary result. Each MAC UE, BIAS UE and ADC UE comprises groups of NAND gates with complementary outputs arranged in NAND-groups, each NAND gate coupled to a differential charge transfer bus through a binary weighted charge transfer capacitor. The analog charge transfer bus is coupled to groups of ADC UEs with an ADC controller which enables and disables the ADC UEs using successive approximation to determine the accumulated multiplication result.

A Gain Balanced Analog Multiply-Accumulator (AMAC) has an inference memory which outputs subsets of inference data comprising X input values and one or more associated W coefficient values. The Gain Balanced AMAC has a number of Analog Multiplier-Accumulator Unit Elements (AMAC UE) in equal number to the number of X input values in each subset of inference data. In each of a series of multiply-accumulate cycles, the X input values and one or more W coefficient values from the inference memory are applied to each AMAC UE to generate a charge corresponding to the multiplication of X input value and W coefficient value of each AMAC UE which is transferred to a shared analog charge bus. The inference memory applies the X input value and W coefficient values of each subset to a different AMAC UE on subsequent cycles to balance the gain of the AMAC such that gain differences from one AMAC UE to another are not cumulative.

Analogue-to-digital converter, ADC, circuitry comprising: successive-approximation circuitry configured in a subconversion operation to draw a charge from a first voltage reference, REF1; compensation circuitry comprising at least one compensation capacitor and configured, in a precharge operation prior to the subconversion operation, to connect the at least one compensation capacitor so that the at least one compensation capacitor stores a compensation charge, and, in the subconversion operation, to connect the at least one compensation capacitor to the first voltage reference so that a charge is injected into the first voltage reference, REF1; and control circuitry, wherein: the successive-approximation circuitry and the compensation circuitry are configured such that one or more parameters defining at least one of said charges are controllable; and the control circuitry is configured to adjust at least one said parameter to adjust an extent to which the charge injected into the first voltage reference, REF1, by the compensation circuitry compensates for the charge drawn from the first voltage reference, REF1, by the successive-approximation circuitry.

In-memory computing architectures and methods of performing multiply-and-accumulate operations are provided. The method includes sequentially shifting bits of first input bytes into each row in an array of memory cells arranged in rows and columns. Each memory cell is activated based on the bit to produce a bit-line current from each activated memory cell in a column on a shared bit-line proportional to a product of the bit and a weight stored therein. Charges produced by a sum of the bit-line currents in a column are accumulated in first charge-storage banks coupled to a shared bit-line in each of the columns. Concurrently, charges from second input bytes accumulated in second charge-storage banks previously coupled to the columns are sequentially converted into output bytes. The charge-storage banks are exchanged after the first input bytes have been accumulated and the charges from the second input bytes converted. The method then repeats.