Abstract:
A method for accelerating a convolution of a kernel matrix over an input matrix for computation of an output matrix using in-memory computation involves storing in different sets of cells, in an array of cells, respective combinations of elements of the kernel matrix or of multiple kernel matrices. To perform the convolution, a sequence of input vectors from an input matrix is applied to the array. Each of the input vectors is applied to the different sets of cells in parallel for computation during the same time interval. The outputs from each of the different sets of cells generated in response to each input vector are sensed to produce a set of data representing the contributions of that input vector to multiple elements of an output matrix. The sets of data generated across the input matrix are used to produce the output matrix.
Abstract:
A neuromorphic computing system includes a synapse array, a switching circuit, a sensing circuit and a processing circuit. The synapse array includes row lines, column lines and synapses. The processing circuit is coupled to the switching circuit and the sensing circuit and is configured to connect a particular column line in the column lines to the first terminal by using the switching circuit, obtain a first voltage value from the particular column line by using the sensing circuit when the particular line is connected to the first terminal, connect the particular column line to the second terminal by using the switching circuit, obtain a second voltage value from the particular column line by using the sensing circuit when the particular line is connected to the second terminal, and estimate a sum-of-product sensing value according to a voltage difference between the first voltage value and the second voltage value.
Abstract:
A neural network system includes a doping well having a first conductivity, a memory string having a plurality of memory cells each include a gate and a source/drain with a second conductivity disposed in the doping well, a buried channel layer having the second conductivity and disposed in the doping well, a word line driver used to apply input voltages corresponding to a plurality of input variations of terms in the sum-of-products operations, a voltage sensing circuit used to apply a constant current into the memory string and to sensing a voltage, a controller used to program/read the memory cells for acquiring a plurality of threshold voltages corresponds to weights of the terms in the sum-of-products operations. When programing/reading the threshold voltages, a first bias voltage is applied to the first doping well; and when sensing the voltage, a second bias voltage is applied to the first doping well.
Abstract:
A method for physically unclonable function-identification (PUF-ID) generation includes: providing a PUF array having programmable resistance memory cells; performing a forming procedure followed by a programming procedure on all of the programmable resistance memory cells of the PUF array; performing an estimation process to estimate randomness of the PUF array, by comparing a reference current of a base unit to a total current passing through all of the programmable resistance memory cells for obtaining a PUF randomness; determining a setting result of randomness based on the estimation process; and generating a PUF-ID according to the setting result of randomness.
Abstract:
A semiconductor structure and a method for manufacturing the same are provided. The semiconductor structure comprises an access device, a dielectric layer, a barrier layer, a first interlayer conductor, a first barrier liner, a second interlayer conductor, a second barrier liner, a memory element and a top electrode layer. The access device has two terminals. The dielectric layer covers the access device. The barrier layer is disposed on the dielectric layer. The first and second interlayer conductors are connected to the two terminals, respectively. The first and second barrier liners are disposed on sidewalls of the first and second interlayer conductors, respectively. The memory element is disposed on the first interlayer conductor. The top electrode layer is disposed on the barrier layer and the memory element and covers the memory element.
Abstract:
A resistive memory device is provided, comprising a bottom electrode, a patterned dielectric layer with a via formed on the bottom electrode, a barrier layer formed at sidewalls and a bottom surface of the via as a liner, a ring-shaped metal layer formed at sidewalls and a bottom surface of the barrier layer, and a ring-shaped metal oxide formed on a top surface of the ring-shaped metal layer.
Abstract:
Metal oxide based memory devices and methods for manufacturing are described herein. A method for manufacturing a memory cell includes forming an insulation layer on an access device followed by forming vias through the insulation layer to expose the first and second access device terminals. First and second interlayer conductors extending through the vias are formed next. Top surfaces of the interlayer conductors are oxidized to form oxide layers. The oxide layer on the first interlayer conductor forms a memory layer. On top of the insulation layer a layer of protection metal is formed covering the oxide layers. The layer of protection metal is patterned and etched to form a top electrode layer covering the memory layer. The oxide layer on the second interlayer conductor is removed. Parallel first and second access lines are then formed on the top electrode layer and the second interlayer conductor, respectively.
Abstract:
A semiconductor device and a manufacturing method and an operating method for the same are provided. The semiconductor device comprises a substrate, a doped region and a stack structure. The doped region is in the substrate. The stack structure is on the substrate. The stack structure comprises a dielectric layer, an electrode layer, a solid electrolyte layer and an ion supplying layer.