Abstract: Numerous embodiments of analog neural memory arrays are disclosed. In certain embodiments, each memory cell in the array has an approximately constant source impedance when that cell is being operated. In certain embodiments, power consumption is substantially constant from bit line to bit line within the array when cells are being read. In certain embodiments, weight mapping is performed adaptively for optimal performance in power and noise.

Abstract: A self-timed sensing architecture for reading a selected cell in an array of non-volatile cells is disclosed. The sensing circuitry generates a signal when a stable sensing value has been obtained from the selected cell, where the stable sensing value indicates the value stored in the selected cell. The signal indicates the end of the sensing operation, causing the stable sensing value to be output as the result of the read operation.

Abstract: A method of forming a semiconductor device includes recessing the upper surface of first and second areas of a semiconductor substrate relative to the third area of the substrate, forming a pair of stack structures in the first area each having a control gate over a floating gate, forming a first source region in the substrate between the pair of stack structures, forming an erase gate over the first source region, forming a block of dummy material in the third area, forming select gates adjacent the stack structures, forming high voltage gates in the second area, forming a first blocking layer over at least a portion of one of the high voltage gates, forming silicide on a top surface of the high voltage gates which are not underneath the first blocking layer, and replacing the block of dummy material with a block of metal material.

Abstract: A memory device includes a semiconductor substrate, first and second regions in the substrate having a conductivity type different than that of the substrate, with a channel region in the substrate extending between the first and second regions. The channel region is continuous between the first and second regions. A first floating gate is disposed over and insulated from a first portion of the channel region. A second floating gate is disposed over and insulated from a second portion of the channel region. A first coupling gate is disposed over and insulated from the first floating gate. A second coupling gate is disposed over and insulated from the second floating gate. A word line gate is disposed over and insulated from a third portion of the channel region between the first and second channel region portions. An erase gate is disposed over and insulated from the word line gate.

Abstract: A memory device, and method of making the same, that includes a substrate of semiconductor material of a first conductivity type, first and second regions spaced apart in the substrate and having a second conductivity type different than the first conductivity type, with a first channel region in the substrate extending between the first and second regions, a first floating gate disposed over and insulated from a first portion of the first channel region adjacent to the second region, a first coupling gate disposed over and insulated from the first floating gate, a first word line gate disposed over and insulated from a second portion of the first channel region adjacent the first region, and a first erase gate disposed over and insulated from the first word line gate.

Abstract: A method of forming memory cells, HV devices and logic devices on a substrate, including recessing the upper surface of the memory cell and HV device areas of the substrate, forming a polysilicon layer in the memory cell and HV device areas, forming first trenches through the first polysilicon layer and into the silicon substrate in the memory cell and HV device areas, filling the first trenches with insulation material, forming second trenches into the substrate in the logic device area to form upwardly extending fins, removing portions of the polysilicon layer in the memory cell area to form floating gates, forming erase and word line gates in the memory cell area, HV gates in the HV device area, and dummy gates in the logic device area from a second polysilicon layer, and replacing the dummy gates with metal gates that wrap around the fins.

Abstract: A memory cell array with memory cells arranged in rows and columns, first sub source lines each connecting together the source regions in one of the rows and in a first plurality of the columns, second sub source lines each connecting together the source regions in one of the rows and in a second plurality of the columns, a first and second erase gate lines each connecting together all of the erase gates in the first and second plurality of the columns respectively, first select transistors each connected between one of first sub source lines and one of a plurality of source lines, second select transistors each connected between one of second sub source lines and one of the source lines, first select transistor line connected to gates of the first select transistors, and a second select transistor line connected to gates of the second select transistors.

Abstract: A method and device for programming a non-volatile memory cell, where the non-volatile memory cell includes a first gate. The non-volatile memory cell is programmed to an initial program state that corresponds to meeting or exceeding a target threshold voltage for the first gate of the non-volatile memory cell. The target threshold voltage corresponds to a target read current. The non-volatile memory cell is read in a first read operation using a read voltage applied to the first gate of the non-volatile memory cell that is less than the target threshold voltage to generate a first read current. The non-volatile memory cell is subjected to additional programming in response to determining that the first read current is greater than the target read current.

Abstract: An artificial neural network device that utilizes one or more non-volatile memory arrays as the synapses. The synapses are configured to receive inputs and to generate therefrom outputs. Neurons are configured to receive the outputs. The synapses include a plurality of memory cells, wherein each of the memory cells includes spaced apart source and drain regions formed in a semiconductor substrate with a channel region extending there between, a floating gate disposed over and insulated from a first portion of the channel region and a non-floating gate disposed over and insulated from a second portion of the channel region. Each of the plurality of memory cells is configured to store a weight value corresponding to a number of electrons on the floating gate. The plurality of memory cells are configured to multiply the inputs by the stored weight values to generate the outputs.

Abstract: Various embodiments of tandem row decoders are disclosed. Each embodiment of a tandem row decoder comprises a word line decoder and a control gate decoder. The tandem row decoder exhibits reduced leakage current on the word line and the control gate line when the tandem row decoder is not enabled.

Abstract: A neural network device with synapses having memory cells each having source and drain regions in a semiconductor substrate with a channel region extending there between, a floating gate over an entirety of the channel region, and a first gate over the floating gate. First lines each electrically connect together the first gates in one of the memory cell rows, second lines each electrically connect together the source regions in one of the memory cell rows, and third lines each electrically connect together the drain regions in one of the memory cell columns. The synapses are configured to receive a first plurality of inputs as electrical voltages on the first lines or on the second lines, and to provide a first plurality of outputs as electrical currents on the third lines.

Abstract: A neural network device with synapses having memory cells each having a floating gate and a first gate over first and second portions of a channel region disposed between source and drain regions, and a second gate over the floating gate or the source region. First lines each electrically connect the first gates in one of the memory cell rows, second lines each electrically connect the second gates in one of the memory cell rows, third lines each electrically connect the source regions in one of the memory cell columns, and fourth lines each electrically connect the drain regions in one of the memory cell columns. The synapses receive a first plurality of inputs as electrical voltages on the first or second lines, and provide a first plurality of outputs as electrical currents on the third or fourth lines.

Abstract: The present invention relates to a flash memory cell with only four terminals and a high voltage row decoder for operating an array of such flash memory cells. The invention allows for fewer terminals for each flash memory cell compared to the prior art, which results in a simplification of the decoder circuitry and overall die space required per flash memory cells. The invention also provides for the use of high voltages on one or more of the four terminals to allow for read, erase, and programming operations despite the lower number of terminals compared to prior art flash memory cells.

Abstract: The present invention relates to systems and methods for implementing wear leveling in a flash memory device that emulates an EEPROM. The embodiments utilize an index array, which stores an index word for each logical address in the emulated EEPROM. Each bit in each index word is associated with a physical address for a physical word in the emulated EEPROM, and the index word keeps track of which physical word is the current word for a particular logical address. The use of the index word enables a wear leveling algorithm that allows for a programming command to a logical address to result in: (i) skipping the programming operation if the data stored in the current word does not contain a “1” that corresponds to a “0” in the data to be stored, (ii) reprogramming one or more bits of the current word in certain situations, or (iii) shifting to and programming the next physical word in certain situations.

Abstract: A memory device that includes a plurality of non-volatile memory cells and a controller. The controller is configured to erase the plurality of memory cells, program each of the memory cells, and for each of the memory cells, measure a threshold voltage applied to the memory cell corresponding to a target current through the memory cell in a first read operation, re-measure a threshold voltage applied to the memory cell corresponding to the target current through the memory cell in a second read operation, and identify the memory cell as defective if a difference between the measured threshold voltage and the re-measured threshold voltage exceeds a predetermined amount.

Abstract: Multiple embodiments are disclosed for enhancing security and preventing hacking of a flash memory device. The embodiments prevent malicious actors from hacking a flash memory chip to obtain data that is stored within the chip. The embodiments include the use of fault detection circuits, address scrambling, dummy arrays, password protection, improved manufacturing techniques, and other mechanisms.

Abstract: A method of forming a semiconductor device where memory cells and some logic devices are formed on bulk silicon while other logic devices are formed on a thin silicon layer over insulation over the bulk silicon of the same substrate. The memory cell stacks, select gate poly, and source regions for the memory devices are formed in the memory area before the logic devices are formed in the logic areas. The various oxide, nitride and poly layers used to form the gate stacks in the memory area are formed in the logic areas as well. Only after the memory cell stacks and select gate poly are formed, and the memory area protected by one or more protective layers, are the oxide, nitride and poly layers used to form the memory cell stacks removed from the logic areas, and the logic devices are then formed.

Abstract: Numerous embodiments are disclosed for providing temperature compensation in a an analog memory array. The analog memory array optionally is a vector-by-matrix multiplier in an analog neuromorphic memory system used in a deep learning neural network. One embodiment comprises measuring an operating temperature within a memory array and applying, by a temperature compensation block, a bias voltage to a terminal of a memory cell in the array, wherein the bias voltage is a function of the operating temperature.

Abstract: Various algorithms are disclosed for verifying the stored weight in a non-volatile memory cell in a neural network following a multilevel programming operation of the non-volatile memory cell by converting the stored weight into a plurality of digital output bits. Circuity, such as an adjustable reference current source, for implementing the algorithms are disclosed.

Abstract: Numerous embodiments of an improved charge pump design are disclosed for generating the high voltages necessary to perform erase and program operations in non-volatile flash memory devices. In these embodiments, each boost stage in the charge pump is modified to overcome a deficiency in prior art charge pumps whereby voltage actually would decrease in the final boost stage. These modifications include the addition of one or more of a clock doubling circuit, a local self-precharge circuit, a feed-forward precharge circuit, a feed-backward precharge circuit, and a hybrid circuit comprising NMOS and PMOS transistors and diodes.