Overlaying on locally dispositioned patterns by ML based dynamic digital corrections (ML-DDC)

    公开(公告)号:US11934762B2

    公开(公告)日:2024-03-19

    申请号:US17396453

    申请日:2021-08-06

    CPC classification number: G06F30/392 G06N20/00 H01L21/68

    Abstract: Systems and methods disclosed are generally related to masklessly developing connections between a chip-group and a design connection point on a substrate. In placement of the chip-group on the substrate, according to certain embodiments the chip-group may be dispositioned relative to an expected position per a substrate layout design, causing a connection misalignment with the design connection point. According to certain embodiments, a machine learning (ML) model is trained on historical and simulated pixel models of chip-group connections and design connection points. Upon determining the chip-group misalignment by a metrology measurement, the trained ML model determines a pixel model to connect the misaligned chip-group, and causes the pixel model to be exposed to a substrate with a digital lithography tool, thereby connecting the dispositioned chip-group to the design connection point.

    Preserving hierarchical structure information within a design file

    公开(公告)号:US11906905B2

    公开(公告)日:2024-02-20

    申请号:US17767020

    申请日:2019-11-15

    CPC classification number: G03F7/70433 G03F7/70508

    Abstract: A verification device for verifying a design file for digital lithography comprises a memory and a controller. The memory comprises the design file. The controller is configured to access the design file and apply one or more compliance rules to the design file to determine compliance of the design file. The compliance rules comprises at least one of detecting non-orthogonal edges within the design file, detecting non-compliant overlapping structures within the design file, and detecting a non-compliant interaction between a reference layer of the design file and a target layer of the design file. The controller is further configured to verify the design file in response to a comparison of a number of non-orthogonal edges, non-compliant overlapping structures and non-compliant interactions to a threshold.

    Data inspection for digital lithography for HVM using offline and inline approach

    公开(公告)号:US12292693B2

    公开(公告)日:2025-05-06

    申请号:US18415430

    申请日:2024-01-17

    Abstract: In embodiments of a digital lithography system, physical design data prepared at a data prep server in a hierarchical data structure. A leaf node comprises a repeater nod, comprising a bitmap image and a plurality of locations at which the bitmap appears in a physical design. At an EYE server, a repeater node bitmap is adjusted based upon, for example, spatial light modulator rotational adjustment and substrate distortion. The adjusted repeater node and the plurality of locations in which the adjusted repeater appears is compared to the repeater of the data prep server and its plurality of locations. In further embodiments, a rasterizer generates a checksum of bitmap to be printed to a substrate, from the EYE server bitmap. The checksum is compared to a checksum of the EYE server bitmap.

    Data inspection for digital lithography for HVM using offline and inline approach

    公开(公告)号:US11914305B2

    公开(公告)日:2024-02-27

    申请号:US17792667

    申请日:2020-02-18

    CPC classification number: G03F7/70508 G03F7/704 G03F7/70291

    Abstract: In embodiments of a digital lithography system, physical design data prepared at a data prep server in a hierarchical data structure. A leaf node comprises a repeater nod, comprising a bitmap image and a plurality of locations at which the bitmap appears in a physical design. At an EYE server, a repeater node bitmap is adjusted based upon, for example, spatial light modulator rotational adjustment and substrate distortion. The adjusted repeater node and the plurality of locations in which the adjusted repeater appears is compared to the repeater of the data prep server and its plurality of locations. In further embodiments, a rasterizer generates a checksum of bitmap to be printed to a substrate, from the EYE server bitmap. The checksum is compared to a checksum of the EYE server bitmap.

    Overlaying on locally dispositioned patterns by ML based dynamic digital corrections (ML-DDC)

    公开(公告)号:US12242789B2

    公开(公告)日:2025-03-04

    申请号:US18439287

    申请日:2024-02-12

    Abstract: Systems and methods disclosed are generally related to masklessly developing connections between a chip-group and a design connection point on a substrate. In placement of the chip-group on the substrate, according to certain embodiments the chip-group may be dispositioned relative to an expected position per a substrate layout design, causing a connection misalignment with the design connection point. According to certain embodiments, a machine learning (ML) model is trained on historical and simulated pixel models of chip-group connections and design connection points. Upon determining the chip-group misalignment by a metrology measurement, the trained ML model determines a pixel model to connect the misaligned chip-group, and causes the pixel model to be exposed to a substrate with a digital lithography tool, thereby connecting the dispositioned chip-group to the design connection point.

Patent Agency Ranking