A voltage-to-time converter circuit receives a first voltage signal and produces a PWM-modulated signal having a duty-cycle proportional to the first voltage signal. A current integrator circuit receives the PWM-modulated signal from the voltage-to-time converter circuit block and produces an output signal by integrating a current signal from a current source over integration time intervals having a duration which is a function of the duty-cycle of the PWM-modulated signal. The current signal is proportional to a second voltage signal. The output signal is accordingly proportional to a product of the first voltage signal and the current signal, which is furthermore proportional to a product of the first voltage signal and the second voltage signal.

A multiply-accumulate operation device, circuit and method are disclosed. In on example, a multiply-accumulate operation device includes input lines, multiplication units, an accumulation unit, a charging unit, and an output unit. Pulse signals having pulse widths corresponding to input values are input to the input lines. The multiplication units generate, based on the pulse signals, charges corresponding to multiplication values obtained by multiplying the input values by weight values. The accumulation unit accumulates a sum of the charges corresponding to the multiplication values. The charging unit charges the accumulation unit at a charging speed associated with its accumulation state. The output unit outputs a multiply-accumulate signal representing a sum of the multiplication values by executing threshold determination using a threshold value associated with the accumulation state of the accumulation unit on a voltage held by the accumulation unit after the charging by the charging unit is started.

A circuit includes an engine to compute analog multiplication results between vectors of a sub-matrix, An analog to digital converter (ADC) generates a digital value for the analog multiplication results computed by the engine. A shifter shifts the digital value of analog multiplication results a predetermined number of bits to generate a shifted result. An adder adds the shifted result to the digital value of a second multiplication result to generate a combined multiplication result.

A circuit includes an engine to compute analog multiplication results between vectors of a sub-matrix, An analog to digital converter (ADC) generates a digital value for the analog multiplication results computed by the engine. A shifter shifts the digital value of analog multiplication results a predetermined number of bits to generate a shifted result. An adder adds the shifted result to the digital value of a second multiplication result to generate a combined multiplication result.

An electronic circuit includes word lines; bit lines intersecting the word lines at a plurality of grid points; and resistive processing units located at the grid points. Baseline stochastic pulse input units are coupled to the word lines; differential stochastic pulse input units are coupled to the word lines; and bitline stochastic pulse input units are coupled to the bit lines. Control circuitry coupled to the pulse input units is configured to cause each of the baseline stochastic pulse input units to generate a baseline pulse train using base input data, each of the differential stochastic pulse input units to generate a differential pulse train using differential input data defining differences from the base input data, and each of the bitline stochastic pulse input units to generate a bitline pulse train using bit line input data. Neural network weights can thus be stored in the resistive processing units.

Input digital bits are split into a first part and a second part. Digital-to-analog converter (DAC) is configured to encode the first part and the second part into analog form as an activation pulse having width equivalent to magnitude of the first part in time units and a delay of a duration that is a fraction of one time unit of the time units, where the fraction is equivalent to magnitude of the second part divided by two raised to power of number of bits in the second part. Crossbar array coupled with the DAC stores weights encoded as analog conductance on resistive memory devices, and is configured to generate analog computation output responsive to the analog form of the input digital bits applied to the crossbar array. Analog-to-digital converter (ADC) coupled with the crossbar array, is configured to digitize the analog computation output from the crossbar array.

Input digital bits are split into a first part and a second part. Digital-to-analog converter (DAC) is configured to encode the first part and the second part into analog form as an activation pulse having width equivalent to magnitude of the first part in time units and a delay of a duration that is a fraction of one time unit of the time units, where the fraction is equivalent to magnitude of the second part divided by two raised to power of number of bits in the second part. Crossbar array coupled with the DAC stores weights encoded as analog conductance on resistive memory devices, and is configured to generate analog computation output responsive to the analog form of the input digital bits applied to the crossbar array. Analog-to-digital converter (ADC) coupled with the crossbar array, is configured to digitize the analog computation output from the crossbar array.