Abstract: A multi-chip module includes a first semiconductor component including a first set of connections having a first pitch dimension and at least a second set of connections having a second pitch dimension, wherein the first pitch dimension is smaller than the second pitch dimension. The multi-chip module further includes a second semiconductor component interconnected with the first set of connections of the first semiconductor component. The multi-chip module further includes at least a third semiconductor component interconnected with the second set of connections of the first semiconductor component and wherein a surface of the third semiconductor component is adhered to a surface of the second semiconductor component, wherein the surfaces at least partially overlap one another.

Abstract: Embodiments of the present invention provide methods for fabricating a semiconductor device with selective oxidation. One method may include providing a semiconductor substrate including a stack of two semiconductor layers; depositing an insulating material on the semiconductor substrate; forming a set of fins; selectively oxidizing one of the semiconductor layers; forming a dummy gate structure and a set of spacers along the sides of the dummy gate structure; forming a source drain region adjacent to the dummy gate structure; removing the dummy gate structure; and releasing the selectively oxidized semiconductor layer.

Abstract: A semiconductor structure is provided. The semiconductor structure includes a first dielectric layer formed on a base structure that has one or more recesses, each comprising contours formed at two or more planar levels. The first dielectric layer is formed along the contours of the one or more recesses. A first electrode is formed on the first dielectric layer. A second dielectric layer is formed over the first dielectric layer and the first electrode. A second electrode is formed over the second dielectric layer. The first electrode, the second dielectric layer and the second electrode form a non-planar capacitor.

Abstract: A computer-implemented method executed on a processor for detecting whether a wafer has been tampered during a semiconductor fabrication process, the method including, at a plurality of patterning steps where lithographic patterns are defined and etched or at a plurality of fabrication processing steps, marking, via an identification tool, each die with an unclonable identification in a memory array, inspecting, via an inspection tool, each of the dies, and removing compromised wafers from a wafer pool during the semiconductor fabrication process.

Abstract: A multi-chip module structure (MCM) having improved heat dissipation includes a plurality of semiconductor chips having a front side mounted on a packaging substrate, wherein each semiconductor chip of the plurality of semiconductor chips further includes a through-substrate vias located at a backside of each semiconductor chip of the plurality of semiconductor chips. A plurality of wire bonds is present that provides interconnect between each semiconductor chip of the plurality of semiconductor chips and is located at the backside of each semiconductor chip of the plurality of semiconductor chips. A heat sink is located above a gap containing the plurality of wire bonds, and a cooling element is located on a surface of the heat sink.

Abstract: A liquid cooled semiconductor package and method for forming a liquid cooled semiconductor package is described. The device includes at least one semiconductor device mounted on a substrate. An impermeable housing is disposed on the substrate with an internal cavity. A liquid coolant is within the internal cavity such that the coolant immerses at least one semiconductor device.

Abstract: A semiconductor structure containing a plurality of stacked vertical field effect transistor (FETs) is provided. After forming a first vertical FET of a first conductivity type at a lower portion of a semiconductor fin, a second vertical FET of a second conductivity type is formed on top of the first vertical FET. The second conductivity type can be opposite to, or the same as, the first conductivity type. A source/drain region of the first vertical FET is electrically connected to a source/drain region of the second vertical FET by a conductive strip structure.

Abstract: A method of forming a resistive random access memory (ReRAM) device is provided. The method includes depositing a lower cap layer on a substrate, depositing a dielectric memory layer on the lower cap layer, and depositing an upper cap layer on the dielectric memory layer. The method further includes removing portions of the lower cap layer to form a lower cap slab, dielectric memory layer to form a dielectric memory slab on the lower cap slab, and upper cap layer to form an upper cap slab on the dielectric memory slab, wherein the lower cap slab, dielectric memory slab, and upper cap slab form a resistive memory element.

Abstract: Non-planar field effect transistor (FET) devices having wrap-around source/drain contacts are provided, as well as methods for fabricating non-planar FET devices with wrap-around source/drain contacts. A method includes forming a non-planar FET device on a substrate, which includes a semiconductor channel layer, and a gate structure in contact with upper and sidewall surfaces of the semiconductor channel layer. First and second source/drain regions are formed on opposite sides of the gate structure in contact with the semiconductor channel layer. First and second recesses are formed in an isolation layer below bottom surfaces of the first and second source/drain regions, respectively. A layer of metallic material is deposited to fill the first and second recesses in the isolation layer with metallic material and form first and second source/drain contacts which surround the first and second source/drain regions.

Abstract: Non-planar field effect transistor (FET) devices having wrap-around source/drain contacts are provided, as well as methods for fabricating non-planar FET devices with wrap-around source/drain contacts. A method includes forming a non-planar FET device on a substrate, which includes a semiconductor channel layer, and a gate structure in contact with upper and sidewall surfaces of the semiconductor channel layer. First and second source/drain regions are formed on opposite sides of the gate structure in contact with the semiconductor channel layer. First and second recesses are formed in an isolation layer below bottom surfaces of the first and second source/drain regions, respectively. A layer of metallic material is deposited to fill the first and second recesses in the isolation layer with metallic material and form first and second source/drain contacts which surround the first and second source/drain regions.

Abstract: Various methods and structures for fabricating a semiconductor structure with vertical vias interconnecting BEOL metallization layers. A first BEOL metallization layer includes a first metallization contact. A second BEOL metallization layer is disposed on the first BEOL metallization layer. The second BEOL metallization layer includes a second metallization contact. A dielectric layer is vertically interposed between the first and second metallization layers. A first vertical via interconnects, through the dielectric layer, the first and second metallization contacts. In the first vertical via, a phase change material non-volatile memory (PCM) is vertically interposed between an upper electrode and a lower electrode. The lower electrode is electrically connected to the first metallization contact. The upper electrode is electrically connected to the second metallization contact.

Abstract: Techniques that facilitate integration of artificial intelligence devices are provided. In one example, a device includes a first dual-damascene layer, a second dual-damascene layer and an artificial intelligence memory device. The first dual-damascene layer comprises a first set of copper connections formed in first dielectric material. The second dual-damascene layer that comprises a second set of copper connections formed in second dielectric material. The artificial intelligence memory device is integrated between the first dual-damascene layer and the second dual-damascene layer. A through-level via (TLV) electrical connection associated with the artificial intelligence memory device provides an interconnection between the first set of copper connections and the second set of copper connections.

Abstract: A semiconductor device includes a plurality of storage elements formed on conductive structures and a cap layer located over the storage elements and the conductive structures. It further includes an interlevel dielectric (ILD) layer over the cap layer, where the ILD layer comprises trenches reaching a top portion of the storage elements, and via openings. The device also has a conductive material formed in the trenches and the via openings, where the conductive material makes contact with the storage elements and forms interlevel vias in the via openings.

Abstract: A method for semiconductor device fabrication includes forming storage elements on conductive structures. An interlevel dielectric (ILD) layer is formed over the storage elements. Trenches are patterned in the ILD layer to expose a top portion of the storage elements. The storage elements where interlevel vias are to be formed is removed. A conductive material is deposited in the trenches and the via openings to concurrently make contact with the storage elements and form interlevel vias in the via openings.

Abstract: A method for manufacturing a semiconductor device includes forming a plurality of transistors on a semiconductor substrate. The formation of the plurality of transistors includes recessing channels of at least two transistors of the plurality of transistors. In the method, a stacked capacitor is formed on the semiconductor substrate, and the stacked capacitor is electrically connected in parallel to the at least two transistors of the plurality of transistors comprising the recessed channels and to an additional one of the plurality of transistors. The stacked capacitor, the at least two transistors and the additional one of the plurality of transistors form a memory cell of a plurality of memory cells of a memory device.

Abstract: Provided are embodiments of a method for forming active regions of a semiconductor device. Embodiments include forming a nanosheet stack on a substrate, forming the nanosheet stack includes forming a sacrificial nanosheet layer on the substrate, and forming a nanosheet layer on the sacrificial nanosheet layer. Embodiments also include forming an etch stop layer on the nanosheet stack, forming a mandrel layer on the etch stop layer, removing portions of the mandrel layer to form a mandrel on the etch stop layer, and forming sidewalls adjacent to sidewalls of the mandrel. The embodiments include depositing a fill layer on exposed portions of the etch stop layer, removing the sidewalls and removing exposed portions of the etch stop layer and the nanosheet stack to expose portions of the substrate.

Abstract: Semiconductor devices and methods of forming the same include forming an etch mask on a stack of alternating dielectric layers and conductor layers. An exposed portion of a dielectric layer and a conductor layer is etched away to form a wordline. The forming and etching steps are repeated, adding additional etch mask material at each iteration, to form respective wordlines at each iteration.

Abstract: Systems and methods for a capacitor based resistive processing unit with symmetrical weight updating include a first capacitor that stores a charge corresponding to a weight value. A readout circuit reads the charge stored in the first capacitor to apply a weight to an input value corresponding to an input signal using the weight value to produce an output. An update circuit updates the weight value stored in the first capacitor, including a second capacitor in communication with the first capacitor to transfer an amount of charge to the first capacitor according to an error of the output by changing a voltage difference across the first capacitor by a voltage change corresponding to the amount of charge, the voltage difference corresponding to the charge stored in the first capacitor.

Abstract: A method for multiple copies of a set of multi-kernel set operations in a hardware accelerated neural network includes a word line for receiving a pixel value of an input image. A bit line communicates a modified pixel value. An analog memory cell including a first capacitor stores a first kernel weight of a first kernel in one of a plurality of kernel sets such that the pixel value is operated on by the first kernel weight to produce the modified pixel value. A charge connection connects the first capacitor to at least a second capacitor storing a second kernel weight of a related kernel of a second one of the plurality of kernel sets such that charge is shared between the first capacitor and at least the second capacitor to normalize the first kernel weight and the second kernel weight.

Abstract: A semiconductor structure with embedded stacked capacitors and a method for fabricating the same are provided. In an embodiment, a method for fabricating logic and memory devices with an embedded stack capacitor includes forming a semiconductor chip having a logic region and a memory region. The method also includes forming back-end-of-line (BEOL) metallization over the logic region but not over the memory region. The method also includes forming a stack capacitor over the memory region.