Abstract: A method of performing automatic tuning on a deep learning model includes: utilizing an instruction-based learned cost model to estimate a first type of operational performance metrics based on a tuned configuration of layer fusion and tensor tiling; utilizing statistical data gathered during a compilation process of the deep learning model to determine a second type of operational performance metrics based on the tuned configuration of layer fusion and tensor tiling; performing an auto-tuning process to obtain a plurality of optimal configurations based on the first type of operational performance metrics and the second type of operational performance metrics; and configure the deep learning model according to one of the plurality of optimal configurations.

Abstract: A semiconductor device includes source/drain regions, a gate structure, a first gate spacer, and a dielectric material. The source/drain regions are over a substrate. The gate structure is laterally between the source/drain regions. The first gate spacer is on a first sidewall of the gate structure, and spaced apart from a first one of the source/drain regions at least in part by a void region. The dielectric material is between the first one of the source/drain regions and the void region. The dielectric material has a gradient ratio of a first chemical element to a second chemical element.

Abstract: A method performed by at least one processor includes: accessing a layout of an integrated circuit (IC), where the layout includes a plurality of patterns in one or more layers of the layout; performing a coloring operation; forming a list comprising at least one uncolorable cell group (UCG) of the layout based on a result of the coloring operation, where each of the at least one UCG comprises at least one uncolorable cell; and performing a first refinement for each UCG on the list. The first refinement is performed through: performing a movement on at least one uncolorable cell of the UCG; determining whether the UCG is colorable; and refining the layout by accepting the movement and removing the UCG from the list in response to the UCG being determined to be colorable.

Abstract: A method performed by at least one processor includes: accessing a layout of an integrated circuit (IC), where the layout includes a plurality of patterns in one or more layers of the layout; performing a coloring operation; forming a list comprising at least one uncolorable cell group (UCG) of the layout based on a result of the coloring operation, where each of the at least one UCG comprises at least one uncolorable cell; and performing a first refinement for each UCG on the list. The first refinement is performed through: performing a movement on at least one uncolorable cell of the UCG; determining whether the UCG is colorable; and refining the layout by accepting the movement and removing the UCG from the list in response to the UCG being determined to be colorable.

Abstract: A pixel structure for an liquid crystal display (LCD) with an embedded touch screen is provided.

Abstract: A pixel structure for an liquid crystal display (LCD) with an embedded touch screen is provided.