Abstract: Numerous embodiments are disclosed for a high voltage generation algorithm and system for generating high voltages necessary for a particular programming operation in analog neural memory used in a deep learning artificial neural network. Compensation measures can be utilized that compensate for changes in voltage or current as the number of cells being programmed changes.

Abstract: The present invention relates to a flash memory device that uses strap cells in a memory array of non-volatile memory cells as source line pull down circuits. In one embodiment, the strap cells are erase gate strap cells. In another embodiment, the strap cells are source line strap cells. In another embodiment, the strap cells are control gate strap cells. In another embodiment, the strap cells are word line strap cells.

Abstract: Configurable input blocks and output blocks and physical layouts are disclosed for analog neural memory systems that utilize non-volatile memory cells. An input block can be configured to support different numbers of arrays arranged in a horizontal direction, and an output block can be configured to support different numbers of arrays arranged in a vertical direction. Adjustable components are disclosed for use in the configurable input blocks and output blocks.

Abstract: 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.

Abstract: Numerous embodiments are disclosed for converting neuron current output by a vector-by-matrix multiplication (VMM) array into neuron current-based time pulses and providing such pulses as an input to another VMM array within an artificial neural network. Numerous embodiments are disclosed for converting the neuron current-based time pulses into analog current or voltage values if an analog input is needed for the VMM array.

Abstract: A method of forming a memory cell includes forming a first polysilicon block over an upper surface of a semiconductor substrate and having top surface and a side surface meeting at a sharp edge, forming an oxide layer with a first portion over the upper surface, a second portion directly on the side surface, and a third portion directly on the sharp edge, performing an etch that thins the oxide layer in a non-uniform manner such that the third portion is thinner than the first and second portions, performing an oxide deposition that thickens the first, second and third portions of the oxide layer, wherein after the oxide deposition, the third portion is thinner than the first and second portions, and forming a second polysilicon block having one portion directly on the first portion of the oxide layer and another portion directly on the third portion of the oxide layer.

Abstract: 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.

Abstract: Testing circuitry and methods are disclosed for use with analog neural memory in deep learning artificial neural networks. The analog neural memory comprises one or more arrays of non-volatile memory cells. The testing circuitry and methods can be utilized during sort tests, qualification tests, and other tests to verify programming operations of one or more cells.

Abstract: Numerous embodiments are disclosed for compensating for differences in the slope of the current-voltage characteristic curve among reference transistors, reference memory cells, and flash memory cells during a read operation in an analog neural memory in a deep learning artificial neural network. The embodiments are able to compensate for slope differences during both sub-threshold and linear operation of reference transistors.

Abstract: A method of forming a semiconductor device by recessing the upper surface of a semiconductor substrate in first and second areas but not a third area, forming a first conductive layer in the first and second areas, forming a second conductive layer in all three areas, removing the first and second conductive layers from the second area and portions thereof from the first area resulting in pairs of stack structures each with a control gate over a floating gate, forming a third conductive layer in the first and second areas, forming a protective layer in the first and second areas and then removing the second conductive layer from the third area, then forming blocks of conductive material in the third area, then etching in the first and second areas to form select and HV gates, and replacing the blocks of conductive material with blocks of metal material.

Abstract: Various embodiments of word line decoders, control gate decoders, bit line decoders, low voltage row decoders, and high voltage row decoders and various types of physical layout designs for non-volatile flash memory arrays in an analog neural system are disclosed. Shared and segmented embodiments of high voltage row decoders are disclosed.

Abstract: Numerous embodiments of power management techniques are disclosed for various operations involving one or more vector-by-matrix multiplication (VMM) arrays within an artificial neural network.

Abstract: A method of forming a memory device that includes forming a first polysilicon layer using a first polysilicon deposition over a semiconductor substrate, forming an insulation spacer on the first polysilicon layer, and removing some of the first polysilicon layer to leave a first polysilicon block under the insulation spacer. A source region is formed in the substrate adjacent a first side surface of the first polysilicon block. A second polysilicon layer is formed using a second polysilicon deposition. The second polysilicon layer is partially removed to leave a second polysilicon block over the substrate and adjacent to a second side surface of the first polysilicon block. A third polysilicon layer is formed using a third polysilicon deposition. The third polysilicon layer is partially removed to leave a third polysilicon block over the source region. A drain region is formed in the substrate adjacent to the second polysilicon block.

Abstract: Testing circuitry and methods are disclosed for use with analog neural memory in deep learning artificial neural networks. The analog neural memory comprises one or more arrays of non-volatile memory cells. The testing circuitry and methods can be utilized during sort tests, qualification tests, and other tests to verify programming operations of one or more cells.

Abstract: Embodiments for ultra-precise tuning of a selected memory cell are disclosed. The selected memory cell optionally is first programmed using coarse programming and fine programming methods. The selected memory cell then undergoes ultra-precise programming through the programming of an adjacent memory cell. As the adjacent memory cell is programmed, capacitive coupling between the floating gate of the adjacent memory cell and the floating gate of the selected memory cell will cause the voltage of the floating gate of the selected memory cell to increase, but in smaller increments than could be achieved by programming the selected memory cell directly. In this manner, the selected memory cell can be programmed with ultra-precise gradations.

Abstract: A memory device with memory cell pairs each having a single continuous channel region, first and second floating gates over first and second portions of the channel region, an erase gate over a third portion of the channel region between the first and second channel region portions, and first and second control gates over the first and second floating gates. For each of the pairs of memory cells, the first region is electrically connected to the second region of an adjacent pair of memory cells in the same active region, and the second region is electrically connected to the first region of an adjacent pair of the memory cells in the same active region.

Abstract: A non-volatile memory device is disclosed. The non-volatile memory device comprises an array of flash memory cells comprising a plurality of flash memory cells organized into rows and columns, wherein the array is further organized into a plurality of sectors, each sector comprising a plurality of rows of flash memory cells, and a row driver selectively coupled to a first row and a second row.

Abstract: A memory device includes a semiconductor substrate with memory cell and logic regions. A floating gate is disposed over the memory cell region and has an upper surface terminating in opposing front and back edges and opposing first and second side edges. An oxide layer has a first portion extending along the logic region and a first thickness, a second portion extending along the memory cell region and has the first thickness, and a third portion extending along the front edge with the first thickness and extending along a tunnel region portion of the first side edge with a second thickness less than the first thickness. A control gate has a first portion disposed on the oxide layer second portion and a second portion vertically over the front edge and the tunnel region portion of the first side edge. A logic gate is disposed on the oxide layer first portion.

Abstract: Memory cells formed on upwardly extending fins of a semiconductor substrate, each including source and drain regions with a channel region therebetween, a floating gate extending along the channel region and wrapping around the fin, a word line gate extending along the channel region and wrapping around the fin, a control gate over the floating gate, and an erase gate over the source region. The control gates are a continuous conductive strip of material. First and second fins are spaced apart by a first distance. Third and fourth fins are spaced apart by a second distance. The second and third fins are spaced apart by a third distance greater than the first and second distances. The continuous strip includes a portion disposed between the second and third fins, but no portion of the continuous strip is disposed between the first and second fins nor between the third and fourth fins.

Abstract: Numerous embodiments for processing the current output of a vector-by-matrix multiplication (VMM) array in an artificial neural network are disclosed. The embodiments comprise a summer circuit and an activation function circuit. The summer circuit and/or the activation function circuit comprise circuit elements that can be adjusted in response to the total possible current received from the VMM to optimize power consumption.