Numerous embodiments of a precision tuning algorithm and apparatus are disclosed for precisely and quickly depositing the correct amount of charge on the floating gate of a non-volatile memory cell within a vector-by-matrix multiplication (VMM) array in an artificial neural network. Selected cells thereby can be programmed with extreme precision to hold one of N different values.

To provide a semiconductor device which can execute the product-sum operation. The semiconductor device includes a first memory cell, a second memory cell, and an offset circuit. First analog data is stored in the first memory cell, and reference analog data is stored in the second memory cell. The first memory cell and the second memory cell supply a first current and a second current, respectively, when a reference potential is applied as a selection signal. The offset circuit has a function of supplying a third current corresponding to a differential current between the first current and the second current. In the semiconductor device, the first memory and the second memory supply a fourth current and a fifth current, respectively, when a potential corresponding to second analog data is applied as a selection signal. By subtracting the third current from a differential current between the fourth current and the fifth current, a current that depends on the sum of products of the first analog data and the second analog data is obtained.

To provide a semiconductor device which can execute the product-sum operation. The semiconductor device includes a first memory cell, a second memory cell, and an offset circuit. First analog data is stored in the first memory cell, and reference analog data is stored in the second memory cell. The first memory cell and the second memory cell supply a first current and a second current, respectively, when a reference potential is applied as a selection signal. The offset circuit has a function of supplying a third current corresponding to a differential current between the first current and the second current. In the semiconductor device, the first memory and the second memory supply a fourth current and a fifth current, respectively, when a potential corresponding to second analog data is applied as a selection signal. By subtracting the third current from a differential current between the fourth current and the fifth current, a current that depends on the sum of products of the first analog data and the second analog data is obtained.

A semiconductor device with a novel structure is provided. The semiconductor device includes a sensor, an amplifier circuit to which a sensor signal of the sensor is input, a sample-and-hold circuit that retains a voltage corresponding to an output signal of an amplifier input to the sample-and-hold circuit, an analog-to-digital converter circuit to which an output signal of the sample-and-hold circuit corresponding to the voltage is input, and an interface circuit. The interface circuit has a function of switching and controlling a first control period in which the sensor signal is input to the amplifier circuit and an output signal of the amplifier circuit is retained in the sample-and-hold circuit and a second control period in which a digital signal obtained by output of the voltage retained in the sample-and-hold circuit to the analog-to-digital converter circuit is output to the interface circuit. In the first control period, the analog-to-digital converter circuit is switched to stop output of the digital signal. The first control period is longer than the second control period.

Systems, apparatuses, and methods related to a neuron built with posits are described. An example system may include a memory device and the memory device may include a plurality of memory cells. The plurality of memory cells can store data including a bit string in an analog format. A neuromorphic operation can be performed on the data in the analog format. The example system may include an analog to digital converter coupled to the memory device. The analog to digital converter may convert the bit string in the analog format stored in at least one of the plurality of memory cells to a format that supports arithmetic operations to a particular level of precision.

A memristor-based circuit includes a voltage generator that applies a series of voltage pulses to a memristor to progressively change the resistance of the memristor. A comparator: receives an input electrical value; receives an electrical value based on the resistance of the memristor; compares the received values; and, based on the comparison, enables the application of the voltage pulses to the memristor by the voltage generator until a defined condition is satisfied. This circuit can be used to enable the memristor to be programmed to a desired resistance value, such as for use as a non-volatile memory. It can also enable the resistance of one memristor to be replicated to another memristor. By counting the number of applied voltage pulses, the circuit can be used as an encoder or analog-to-digital converter. Other variants of the circuit enable construction of a decoder or digital-to-analog converter, and an authentication circuit.

A high bandwidth memory system includes a motherboard; and a semiconductor package coupled to the motherboard. The semiconductor package includes a package substrate mounted on the motherboard and including signal lines providing a plurality of channels; a first semiconductor device mounted on the package substrate and including a first physical layer (PHY) circuit; and a second semiconductor device mounted on the package substrate and including a second PHY circuit. The first semiconductor device and the second semiconductor device exchange a data signal with each other through the plurality of channels, the data signal is a multilevel signal having M levels, where M is a natural number greater than 2, and the first PHY circuit compensates for distortion of the channels and performs digital signal processing to compensate for a mismatch between the channels.

A high bandwidth memory system includes a motherboard; and a semiconductor package coupled to the motherboard. The semiconductor package includes a package substrate mounted on the motherboard and including signal lines providing a plurality of channels; a first semiconductor device mounted on the package substrate and including a first physical layer (PHY) circuit; and a second semiconductor device mounted on the package substrate and including a second PHY circuit. The first semiconductor device and the second semiconductor device exchange a data signal with each other through the plurality of channels, the data signal is a multilevel signal having M levels, where M is a natural number greater than 2, and the first PHY circuit compensates for distortion of the channels and performs digital signal processing to compensate for a mismatch between the channels.

A neuromorphic system according to an embodiment of the invention includes an input signal section that generates an input signal, a synapse section that includes a plurality of synaptic units that receive the input signal and makes a current to flow according to a set weight, each of the plurality of synaptic units including a plurality of non-volatile memory cells capable of selectively storing a logical state, the non-volatile memory cells being arranged in a memory array that include input electrode lines and output electrode lines crossing each other, and generates an output signal for each output electrode line by the input signal, a digital calculation section that digitizes the output signal generated for each output electrode line and calculates a sum of the digitized output signals, and a controller section that controls the input signal section, the synapse section, and the digital calculation section, and the controller section designates the number of digitized digits for each output electrode line and stores the logic state in the plurality of non-volatile memory cells according to a predetermined weight in each of the plurality of synaptic units, causes the input signal generated by the input signal section to be applied to each of a plurality of non-volatile memory cells of each of the plurality of synaptic units through the input electrode lines, generates, as the output signal, a sum of currents flowing from the plurality of non-volatile memory cells of each of the plurality of synaptic units by the applied input signal for each output electrode line, and causes the digital calculation section to digitize the output signal generated for each output electrode line according to the number of digits and calculate the sum of the digitized output signals.

A neuromorphic system according to an embodiment of the invention includes an input signal section that generates an input signal, a synapse section that includes a plurality of synaptic units that receive the input signal and makes a current to flow according to a set weight, each of the plurality of synaptic units including a plurality of non-volatile memory cells capable of selectively storing a logical state, the non-volatile memory cells being arranged in a memory array that include input electrode lines and output electrode lines crossing each other, and generates an output signal for each output electrode line by the input signal, a digital calculation section that digitizes the output signal generated for each output electrode line and calculates a sum of the digitized output signals, and a controller section that controls the input signal section, the synapse section, and the digital calculation section, and the controller section designates the number of digitized digits for each output electrode line and stores the logic state in the plurality of non-volatile memory cells according to a predetermined weight in each of the plurality of synaptic units, causes the input signal generated by the input signal section to be applied to each of a plurality of non-volatile memory cells of each of the plurality of synaptic units through the input electrode lines, generates, as the output signal, a sum of currents flowing from the plurality of non-volatile memory cells of each of the plurality of synaptic units by the applied input signal for each output electrode line, and causes the digital calculation section to digitize the output signal generated for each output electrode line according to the number of digits and calculate the sum of the digitized output signals.