A method for implementing a neural network system in an integrated circuit includes presenting digital pulses to word line inputs of a matrix vector multiplier including a plurality of word lines, 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, each digital pulse having a pulse width proportional to an analog quantity. During a charge collection time frame charge collected on each of the summing bit lines from current flowing in the programmable Vt transistor is summed. During a pulse generating time frame digital pulses are generated having pulse widths proportional to the amount of charge that was collected on each summing bit line during the charge collection time frame.

A semiconductor memory cell includes a floating body region configured to be charged to a level indicative of a state of the memory cell; a first region in electrical contact with said floating body region; a second region in electrical contact with said floating body region and spaced apart from said first region; and a gate positioned between said first and second regions. The cell may be a multi-level cell. Arrays of memory cells are disclosed for making a memory device. Methods of operating memory cells are also provided.

Methods of maintaining a state of a memory cell without interrupting access to the memory cell are provided, including applying a back bias to the cell to offset charge leakage out of a floating body of the cell, wherein a charge level of the floating body indicates a state of the memory cell; and accessing the cell.

A semiconductor memory instance is provided that includes an array of memory cells. The array includes a plurality of semiconductor memory cells arranged in at least one column and at least one row. Each of the semiconductor memory cells includes a floating body region configured to be charged to a level indicative of a state of the memory cell. Further includes are a plurality of buried well regions, wherein each of the buried well regions can be individually selected, and a decoder circuit to select at least one of the buried well regions.

A 3-dimensional array of NOR memory strings being organized by planes of NOR memory strings, in which (i) the storage transistors in the NOR memory strings situated in a first group of planes are configured to be programmed, erased, program-inhibited or read in parallel, and (ii) the storage transistors in NOR memory strings situated within a second group of planes are configured for storing resource management data relating to data stored in the storage transistors of the NOR memory strings situated within the first group of planes, wherein the storage transistors in NOR memory strings in the second group of planes are configured into sets.

A 3D memory device, the device including: a plurality of memory cells, where each memory cell of the plurality of memory cells includes at least one memory transistor, where each of the at least one memory transistor includes a source, a drain, and a channel; and a plurality of bit-line pillars, where each bit-line pillar of the plurality of bit-line pillars is directly connected to a plurality of the source or the drain, where the bit-line pillars are vertically oriented, where the channel is horizontally oriented, and where the device includes a temperature sensor.

Systems and methods of configuring a fixed memory array of an integrated circuit with coefficients of one or more applications includes identifying a utilization constraint type of the fixed memory array from a plurality of distinct utilization constraint types based on computing attributes of the one or more applications; identifying at least one coefficient mapping technique from a plurality of distinct coefficient mapping techniques that addresses the utilization constraint type; configuring the fixed memory array according to the at least one coefficient mapping technique, wherein configuring the array includes at least setting within the array the coefficients of the one or more applications in an arrangement prescribed by the at least one coefficient mapping technique that optimizes a computational utilization of the fixed memory array.

A memory device includes a high density or 3D data memory and a 3D reference memory. The reference memory is used to generate a reference signal used to sense data in the data memory. Conversion circuitry converts signals from one memory cell or a group of memory cells in the reference memory into a reference signal. The reference signal is applied to a sense amplifier to sense data stored in a selected memory cell in the data memory.

A semiconductor memory cell and arrays of memory cells are provided In at least one embodiment, a memory cell includes a substrate having a top surface, the substrate having a first conductivity type selected from a p-type conductivity type and an n-type conductivity type; a first region having a second conductivity type selected from the p-type and n-type conductivity types, the second conductivity type being different from the first conductivity type, the first region being formed in the substrate and exposed at the top surface; a second region having the second conductivity type, the second region being formed in the substrate, spaced apart from the first region and exposed at the top surface; a buried layer in the substrate below the first and second regions, spaced apart from the first and second regions and having the second conductivity type; a body region formed between the first and second regions and the buried layer, the body region having the first conductivity type; a gate positioned between the first and second regions and above the top surface; and a nonvolatile memory configured to store data upon transfer from the body region.

A thin-film storage transistor includes a charge storage film provided between a channel region and a gate conductor where the charge storage film includes a tunneling dielectric layer formed adjacent the channel region and a charge trapping layer formed adjacent the tunneling dielectric layer. In some embodiments, the charge trapping layer is a layer including silicon, silicon oxide and silicon nitride materials. In one embodiment, the charge trapping layer is a layer including a mixture of silicon, silicon oxide and silicon nitride materials, where the silicon oxide and silicon nitride may or may not be their respective stoichiometric compounds.