A nanostructured cross-wire memory architecture is provided that can interface with conventional semiconductor technologies and be electrically accessed and read. The architecture links lower and upper sets of generally parallel nanowires oriented crosswise, with a memory element that has a characteristic conductance. Each nanowire end is attached to an electrode. Conductance of the linkages in the gap between the wires encodes the information. The nanowires may be highly-conductive, self-assembled, nucleic acid-based nanowires enhanced with dopants including metal ions, carbon, metal nanoparticles and intercalators. Conductance of the memory elements can be controlled by sequence, length, conformation, doping, and number of pathways between nanowires. A diode can also be connected in series with each of the memory elements. Linkers may also be redox or electroactive switching molecules or nanoparticles where the charge state changes the resistance of the memory element.

Disclosed are systems and methods for monolithically-integrating an artificial intelligence processor system and a nanotube memory system on the same die to achieve high memory density and low power consumption.

Embodiments of the present disclosure are directed towards techniques to provide structural integrity for a memory device comprising a memory array. In one embodiment, the device may comprise a memory array having at least a plurality of wordlines disposed in a memory region of a die, and a first fill layer deposited between adjacent wordlines of the plurality of wordlines in the memory region, to provide structural integrity for the memory array. At least a portion of a periphery region of the die adjacent to the memory region may be substantially filled with a second fill layer that is different than the first fill layer. Other embodiments may be described and/or claimed.

In one embodiment, a semiconductor storage device includes a first interconnect extending in a first direction, a plurality of second interconnects extending in a second direction different from the first direction, and a plurality of first insulators provided alternately with the second interconnects. The device further includes a resistance change film provided between the first interconnect and at least one of the second interconnects and including a first metal layer or a first semiconductor layer that includes a first face provided on a first interconnect side and a second face provided on a second interconnect side, at least any of the first face and the second face having a curved plane shape.

A nanostructured cross-wire memory architecture is provided that can interface with conventional semiconductor technologies and be electrically accessed and read. The architecture links lower and upper sets of generally parallel nanowires oriented crosswise, with a memory element that has a characteristic conductance. Each nanowire end is attached to an electrode. Conductance of the linkages in the gap between the wires encodes the information. The nanowires may be highly-conductive, self-assembled, nucleic acid-based nanowires enhanced with dopants including metal ions, carbon, metal nanoparticles and intercalators. Conductance of the memory elements can be controlled by sequence, length, conformation, doping, and number of pathways between nanowires. A diode can also be connected in series with each of the memory elements. Linkers may also be redox or electroactive switching molecules or nanoparticles where the charge state changes the resistance of the memory element.

A semiconductor memory device includes memory cell arrays that include a plurality of memory cells. A first control circuit with control transistors of a first conductivity type is in a first region below the memory cell arrays. A second control circuit includes a first transistor of a first conductivity type connected in parallel to a second transistor of a second conductivity type. One of the first and second transistors is connected to an end of at least one control transistor. The second control circuit delivers a voltage to the plurality of control transistors. The first transistor is disposed in the first region. The second transistor is disposed in a second region adjacent to the first region. The second region is below a gap between adjacent memory cell arrays.

Carbon nanotube template arrays may be edited to form connections between proximate nanotubes and/or to delete undesired nanotubes or nanotube junctions.

A semiconductor memory device includes memory cell arrays that include a plurality of memory cells. A first control circuit with control transistors of a first conductivity type is in a first region below the memory cell arrays. A second control circuit includes a first transistor of a first conductivity type connected in parallel to a second transistor of a second conductivity type. one of the first and second transistors is connected to an end of at least one control transistor. The second control circuit delivers a voltage to the plurality of control transistors. The first transistor is disposed in the first region. The second transistor is disposed in a second region adjacent to the first region. The second region is below a gap between adjacent memory cell arrays.

Embodiments of the present disclosure are directed towards techniques to provide structural integrity for a memory device comprising a memory array. In one embodiment, the device may comprise a memory array having at least a plurality of wordlines disposed in a memory region of a die, and a first fill layer deposited between adjacent wordlines of the plurality of wordlines in the memory region, to provide structural integrity for the memory array. At least a portion of a periphery region of the die adjacent to the memory region may be substantially filled with a second fill layer that is different than the first fill layer. Other embodiments may be described and/or claimed.

In one embodiment, a semiconductor storage device includes a first interconnect extending in a first direction, a plurality of second interconnects extending in a second direction different from the first direction, and a plurality of first insulators provided alternately with the second interconnects. The device further includes a resistance change film provided between the first interconnect and at least one of the second interconnects and including a first metal layer or a first semiconductor layer that includes a first face provided on a first interconnect side and a second face provided on a second interconnect side, at least any of the first face and the second face having a curved plane shape.