G06G7/161

Resistive memory device for matrix-vector multiplications

A device performs a matrix-vector multiplication of a matrix with a vector. The device includes a crossbar array having row lines, column lines and junctions arranged between the row lines and the column lines. Each junction includes a programmable resistive element and an access element for accessing the programmable resistive element. The device further includes a signal generator configured to apply programming signals to the resistive elements to program conductance values for the matrix-vector multiplication. The device further includes a readout circuit and control circuitry configured to control the signal generator and the readout circuit. The readout circuit is configured to apply read voltages having a positive voltage sign and negative read voltages having a negative voltage sign to the row lines of the crossbar array. The readout circuit is further configured to read out column currents of the plurality of column lines of the crossbar array.

Resistive memory device for matrix-vector multiplications

A device performs a matrix-vector multiplication of a matrix with a vector. The device includes a crossbar array having row lines, column lines and junctions arranged between the row lines and the column lines. Each junction includes a programmable resistive element and an access element for accessing the programmable resistive element. The device further includes a signal generator configured to apply programming signals to the resistive elements to program conductance values for the matrix-vector multiplication. The device further includes a readout circuit and control circuitry configured to control the signal generator and the readout circuit. The readout circuit is configured to apply read voltages having a positive voltage sign and negative read voltages having a negative voltage sign to the row lines of the crossbar array. The readout circuit is further configured to read out column currents of the plurality of column lines of the crossbar array.

Resistive Memory Device For Matrix-Vector Multiplications

A device performs a matrix-vector multiplication of a matrix with a vector. The device includes a crossbar array having row lines, column lines and junctions arranged between the row lines and the column lines. Each junction includes a programmable resistive element and an access element for accessing the programmable resistive element. The device further includes a signal generator configured to apply programming signals to the resistive elements to program conductance values for the matrix-vector multiplication. The device further includes a readout circuit and control circuitry configured to control the signal generator and the readout circuit. The readout circuit is configured to apply read voltages having a positive voltage sign and negative read voltages having a negative voltage sign to the row lines of the crossbar array. The readout circuit is further configured to read out column currents of the plurality of column lines of the crossbar array.

Improved analog computing using dynamic amplitude scaling and methods of use
20200265198 · 2020-08-20 ·

An improved integrator for use in physical analog-computing systems is disclosed, featuring real-time dynamic amplitude scaling schemas that make use of an injected correction factor responsive to a contemporaneous change in an input dynamic-amplitude-scaling compensation factor. The injected correction factor is designed to reduce or eliminate transient output perturbations due to the amplitude scaling change. The disclosures discussed have real-world applications for physical analog computers and hybrid computers used to control and manage many types of industrial-control systems.

Improved analog computing using dynamic amplitude scaling and methods of use
20200265198 · 2020-08-20 ·

An improved integrator for use in physical analog-computing systems is disclosed, featuring real-time dynamic amplitude scaling schemas that make use of an injected correction factor responsive to a contemporaneous change in an input dynamic-amplitude-scaling compensation factor. The injected correction factor is designed to reduce or eliminate transient output perturbations due to the amplitude scaling change. The disclosures discussed have real-world applications for physical analog computers and hybrid computers used to control and manage many types of industrial-control systems.

APPARATUS AND METHOD FOR COMBINING ANALOG NEURAL NET WITH FPGA ROUTING IN A MONOLITHIC INTEGRATED CIRCUIT

A user programmable integrated circuit includes a user-programmable routing network including a plurality of interconnect conductors selectively couplable to one another by user-programmable elements. A plurality of matrix vector multipliers, each have a plurality of word lines, each word line coupled to a different first one of the one of the interconnect conductors of the user-programmable routing network, the word lines forming intersections with a plurality of summing bit lines, a programmable Vt transistor at each intersection having a gate connected to the intersecting word line, a source connected to a fixed potential and a drain connected to the intersecting summing bit line. A charge-to-pulse-width converter circuit is associated with each one of the matrix vector multipliers, each having an input coupled to one of the summing bit lines, and a pulse output coupled to a different second one of the interconnect conductors of the user-programmable routing network.

Multiplier circuit, corresponding device and method

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.

Multiplier circuit, corresponding device and method

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.

Analog sub-matrix computing from input matrixes

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.

Analog sub-matrix computing from input matrixes

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.