Abstract:
A method for generating a data set on an integrated circuit including programmable resistance memory cells includes applying a forming pulse to all members of a set of the programmable resistance memory cells. The forming pulse has a forming pulse level characterized by inducing a change in resistance in a first subset of the set from an initial resistance range to an intermediate resistance range, while after the forming pulse a second subset of the set has a resistance outside the intermediate range. The method includes applying a programming pulse to the first and second subsets. The programming pulse has a programming pulse level characterized by inducing a change in resistance of the first subset from the intermediate range to a first final range, while after the programming pulse the second subset has a resistance in a second final range, whereby the first and second subsets store said data set.
Abstract:
A memory architecture has improved controllability of operations for bipolar current directions used to write data in programmable resistance memory cells, including ReRAM cells based on metal oxide memory materials. Instead of a fixed gate voltage on a specific decoder transistor or cell selection device, and a control voltage set to values that cause the decoder transistor or cell selection device to operate in a fully-on mode for one current direction or in a current moderating mode with opposite current direction. Using this technology allows symmetrical or close to symmetrical operation in both current directions with little or no effect on the array complexity.
Abstract:
A memory structure and a manufacturing method for the same are disclosed. The memory structure comprises a lower electrode, an upper insulating layer, a material layer, a dielectric film, and an upper electrode. The upper insulating layer is on the lower electrode. The material layer is on the upper insulating layer. The upper insulating layer and the material layer have a common opening to expose a portion of the lower electrode. The dielectric film is on the exposed portion of the lower electrode. The dielectric film and the material layer contain a same first transition metal. The upper electrode is on the dielectric film and fills the common opening.
Abstract:
A method is provided for manufacturing a memory. An insulating layer is formed over an array of interlayer conductors, and etched to define a first opening corresponding to a first interlayer conductor in the array, where the etching stops at a first top surface of the first interlayer conductor. A metal oxide layer is formed on the first top surface. A first layer of barrier material is deposited conformal with and contacting the metal oxide layer and surfaces of the first opening. Subsequently the insulating layer is etched to define a second opening corresponding to a second interlayer conductor in the array, where the etching stops at a second top surface of the second interlayer conductor. A second layer of barrier material is deposited conformal with and contacting the first layer of barrier material in the first opening. The first opening is filled with a conductive material.
Abstract:
A memory device comprises a substrate, a first electrode layer, a spacer, a memory layer and a second electrode layer. The substrate has a recess. The first electrode layer is formed in the recess and has a top surface exposed from an opening of the recess. The spacer covers on a portion of the top surface, so as to define a contact area on the top surface. The memory layer is formed on the contact area. The second electrode layer is formed on the memory layer and electrically connected to the memory layer.
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:
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.
Abstract:
An in-memory computation device includes multiple computation blocks, a first reference weight block, and an output result generator. The computation blocks have multiple weighting values, receive multiple input signals respectively, and generate multiple computation results. Each of the computation blocks generates each of the computation results according to each of the corresponding input signals and corresponding weighting values. The first reference weight block provides a first reference resistance according to multiple reference weighting values and generates a first reference signal according to the first reference resistance and a read voltage. The output result generator generates multiple output computation results according to the first reference signal and the computation results.
Abstract:
The disclosure provides a cache device, which includes: a first transistor having a control terminal, a first terminal, and a second terminal, in which the first terminal of the first transistor is coupled to an input voltage, and the second terminal of the first transistor is coupled to a storage node; an inverter having an input terminal and an output terminal, in which the input terminal is coupled to the storage node; and a second transistor having a control terminal, a first terminal, and a second terminal, in which the first terminal of the second transistor is coupled to the output terminal of the inverter, and the second terminal of the second transistor is configured to output a read voltage.
Abstract:
An artificial neural network operation circuit and an in-memory computation device of the artificial neural network operation circuit are proposed. The in-memory computation device includes a memory cell array, a compensation memory cell string, and an operator. The memory cell array has a plurality of memory cells to store a plurality of weight values. The memory cell array has a plurality of word lines and a plurality of bit lines. Each compensation memory cell of the compensation memory cell string stores a unit weight value. The operator multiplies a signal on a compensation bit line by peak weight information of the weight values to generate a first signal and adds the first signal to each signal on the bit lines to obtain a plurality of computation results, respectively.