Abstract: Examples for ultra-precise tuning of a selected memory cell are disclosed. In one example, a method of programming a first memory cell in a neural memory to a target value is disclosed, the method comprising programming a second memory cell by applying programming voltages to terminals of the second memory cell; and determining if an output of the first memory cell has reached the target value.

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: 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 stack gate structure for a non-volatile memory array has a semiconductor substrate having a plurality of substantially parallel spaced apart active regions, with each active region having an axis in a first direction. A first insulating material is between each stack gate structure in the second direction perpendicular to the first direction. Each stack gate structure has a second insulating material over the active region, a charge holding gate over the second insulating material, a third insulating material over the charge holding gate, and a first portion of a control gate over the third insulating material. A second portion of the control gate is over the first portion of the control gate and over the first insulating material adjacent thereto and extending in the second direction. A fourth insulating material is over the second portion of the control gate.

Abstract: A stack gate structure for a non-volatile memory array has a semiconductor substrate having a plurality of substantially parallel spaced apart active regions, with each active region having an axis in a first direction. A first insulating material is between each stack gate structure in the second direction perpendicular to the first direction. Each stack gate structure has a second insulating material over the active region, a charge holding gate over the second insulating material, a third insulating material over the charge holding gate, and a first portion of a control gate over the third insulating material. A second portion of the control gate is over the first portion of the control gate and over the first insulating material adjacent thereto and extending in the second direction. A fourth insulating material is over the second portion of the control gate.

Abstract: A stack gate structure for a non-volatile memory array has a semiconductor substrate having a plurality of substantially parallel spaced apart active regions, with each active region having an axis in a first direction. A first insulating material is between each stack gate structure in the second direction perpendicular to the first direction. Each stack gate structure has a second insulating material over the active region, a charge holding gate over the second insulating material, a third insulating material over the charge holding gate, and a first portion of a control gate over the third insulating material. A second portion of the control gate is over the first portion of the control gate and over the first insulating material adjacent thereto and extending in the second direction. A fourth insulating material is over the second portion of the control gate.

Abstract: A method of operating a memory cell that comprises first and second regions spaced apart in a substrate with a channel region therebetween, a floating gate disposed over the channel region and the fir region, a control gate disposed over the channel region and laterally adjacent to the floating gate with a portion disposed over the floating gate, and a coupling gate disposed over the first region and laterally adjacent to the floating gate. A method of erasing the memory cell includes applying a positive voltage to the control gate and a negative voltage to the coupling gate. A method of reading the memory cell includes applying positive voltages to the control gate, to the coupling gate, and to one of the first and second regions.

Abstract: A method of operating a memory cell that comprises first and second regions spaced apart in a substrate with a channel region therebetween, a floating gate disposed over the channel region and the first region, a control gate disposed over the channel region and laterally adjacent to the floating gate with a portion disposed over the floating gate, and a coupling gate disposed over the first region and laterally adjacent to the floating gate. A method of erasing the memory cell includes applying a positive voltage to the control gate and a negative voltage to the coupling gate. A method of reading the memory cell includes applying positive voltages to the control gate, to the coupling gate, and to one of the first and second regions.

Abstract: A method of operating a memory cell that comprises first and second regions spaced apart in a substrate with a channel region therebetween, a floating gate disposed over the channel region and the first region, a control gate disposed over the channel region and laterally adjacent to the floating gate with a portion disposed over the floating gate, and a coupling gate disposed over the first region and laterally adjacent to the floating gate. A method of erasing the memory cell includes applying a positive voltage to the control gate and a negative voltage to the coupling gate. A method of reading the memory cell includes applying positive voltages to the control gate, to the coupling gate, and to one of the first and second regions.

Abstract: A stack gate structure for a non-volatile memory array has a semiconductor substrate having a plurality of substantially parallel spaced apart active regions, with each active region having an axis in a first direction. A first insulating material is between each stack gate structure in the second direction perpendicular to the first direction. Each stack gate structure has a second insulating material over the active region, a charge holding gate over the second insulating material, a third insulating material over the charge holding gate, and a first portion of a control gate over the third insulating material. A second portion of the control gate is over the first portion of the control gate and over the first insulating material adjacent thereto and extending in the second direction. A fourth insulating material is over the second portion of the control gate.

Abstract: An array of non-volatile memory cells with spaced apart first regions extending in a row direction and second regions extending in a column direction, with a channel region defined between each second region and its associated first region. A plurality of spaced apart word line gates each extending in the row direction and positioned over a first portion of a channel region. A plurality of spaced apart floating gates are positioned over second portions of the channel regions. A plurality of spaced apart coupling gates each extending in the row direction and over the floating gates. A plurality of spaced apart metal strapping lines each extending in the row direction and overlying a coupling gate. A plurality of spaced apart erase gates each extending in the row direction and positioned over a first region and adjacent to a floating gate and coupling gate.

Abstract: An array of non-volatile memory cells with spaced apart first regions extending in a row direction and second regions extending in a column direction, with a channel region defined between each second region and its associated first region. A plurality of spaced apart word line gates each extending in the row direction and positioned over a first portion of a channel region. A plurality of spaced apart floating gates are positioned over second portions of the channel regions. A plurality of spaced apart coupling gates each extending in the row direction and over the floating gates. A plurality of spaced apart metal strapping lines each extending in the row direction and overlying a coupling gate. A plurality of spaced apart erase gates each extending in the row direction and positioned over a first region and adjacent to a floating gate and coupling gate.

Abstract: A method of operating a memory cell that comprises first and second regions spaced apart in a substrate with a channel region therebetween, a floating gate disposed over the channel region and the first region, a control gate disposed over the channel region and laterally adjacent to the floating gate with a portion disposed over the floating gate, and a coupling gate disposed over the first region and laterally adjacent to the floating gate. A method of erasing the memory cell includes applying a positive voltage to the control gate and a negative voltage to the coupling gate. A method of reading the memory cell includes applying positive voltages to the control gate, to the coupling gate, and to one of the first and second regions.

Abstract: Described is a power multiplexer that alternately transmits zero, supply voltage, and a relatively high voltage to a common output node. The power multiplexer includes low-impedance voltage switches, at least one of which includes a well-voltage select circuit. The well-voltage select circuit adjusts the well bias on a power-switching transistor, and consequently protects the power-switching transistor from damage caused by gate breakdown and forwarding biasing of the well.

Abstract: A CPLD employs a low-voltage, non-degenerative transmitter circuit to eliminate the need for a dedicated control pin to provide the relatively high voltage levels required to verify the program states of programmable memory cells. Eliminating the need for a dedicated control pin frees up valuable chip real estate for the inclusion of an additional general-purpose input/output pin.

Abstract: Described are circuits and methods for automatically measuring the program threshold voltage VTP and the erase threshold voltage VTE of EEPROM cells. The measured threshold voltages are employed to measure tunnel-oxide thickness and to determine optimal program and erase voltage levels for EEPROM circuits. One embodiment automatically sets the program and erase voltages based on the measured threshold voltages.

Abstract: A CPLD employs a low-voltage, non-degenerative transmitter circuit to eliminate the need for a dedicated control pin to provide the relatively high voltage levels required to verify the program states of programmable memory cells. Eliminating the need for a dedicated control pin frees up valuable chip real estate for the inclusion of an additional general-purpose input/output pin.

Abstract: A ramp-up circuit on an integrated circuit receives a relatively high program (erase) voltage for changing the program state of a memory cell. The ramp-up circuit gradually raises the program (erase) voltage to prevent damage to the memory cell. The ramp-up circuit includes a pass gate and associated control circuitry that provides a controlled, ramped-up version of the program (erase) voltage to the memory cell without raising internal circuit nodes above the program (erase) voltage.