An integrated circuit design method includes receiving an integrated circuit design, and determining a floor plan for the integrated circuit design. The floor plan includes an arrangement of a plurality of functional cells and a plurality of tap cells. Potential latchup locations in the floor plan are determined, and the arrangement of at least one of the functional cells or the tap cells is modified based on the determined potential latchup locations.

A graph neural network to predict net parasitics and device parameters by transforming circuit schematics into heterogeneous graphs and performing predictions on the graphs. The system may achieve an improved prediction rate and reduce simulation errors.

In an embodiment, an integrated circuit includes transistors in different active regions, electrically isolated using single diffusion break isolation. The single diffusion break isolation includes a first dummy transistor that has a different threshold voltage than the transistors in either active region for which the single diffusion break is creating isolation. The first dummy transistor may have lower leakage current than transistors in either active region, creating effective isolation between the active regions and consuming relatively small amounts of power due to the lower leakage currents.

In an embodiment, an integrated circuit includes transistors in different active regions, electrically isolated using single diffusion break isolation. The single diffusion break isolation includes a first dummy transistor that has a different threshold voltage than the transistors in either active region for which the single diffusion break is creating isolation. The first dummy transistor may have lower leakage current than transistors in either active region, creating effective isolation between the active regions and consuming relatively small amounts of power due to the lower leakage currents.

A non-transitory computer-readable recording medium storing a training data generation program for causing a computer to execute processing including: calculating, for each of a first plurality of pieces of circuit information, a characteristic impedance of a circuit included in the each of the first plurality of pieces of circuit information; classifying the first plurality of pieces of circuit information based on the calculated characteristic impedance; selecting one or more of pieces of circuit information from a second plurality of pieces of circuit information, each of the second plurality of pieces of circuit information being, among the first plurality of pieces of circuit information, a piece of circuit information classified into a first group by the classifying; and generating training data for machine learning based on the selected one or more of pieces of circuit information.

Methods and systems are described for generating assessment maps. A method includes receiving a first vector map comprising a first set of vectors each indicating a distortion of a particular location on a substrate and generating a second vector map indicating a change in direction of a magnitude of the distortion of the particular location on the substrate. The method further includes generating a third vector map comprising vectors reflecting reduced noise in distortions across the plurality of locations on the substrate and generating a fourth vector map projecting a direction component of each vector component in the third set of vectors to a radial direction. The method further includes generating a fifth vector map by grouping the vectors of the fourth set of vectors and determining a magnitude associated with each group of vectors.

Methods and systems are described for generating assessment maps. A method includes receiving a first vector map comprising a first set of vectors each indicating a distortion of a particular location on a substrate and generating a second vector map indicating a change in direction of a magnitude of the distortion of the particular location on the substrate. The method further includes generating a third vector map comprising vectors reflecting reduced noise in distortions across the plurality of locations on the substrate and generating a fourth vector map projecting a direction component of each vector component in the third set of vectors to a radial direction. The method further includes generating a fifth vector map by grouping the vectors of the fourth set of vectors and determining a magnitude associated with each group of vectors.

Implementations disclosed herein may include receiving from a user a selection of at least one die, a package type, and at least one test condition; generating, using a processor, a product die configuration and a product package configuration using a predictive modeling module and the at least one die and the package type; generating a graphic design system file; generating a package bonding diagram; generating a product spice model of the discrete device product using a technology computer aided design module; generating, using a processor, one or more datasheet characteristics of the discrete device product with the product SPICE model; generating a product datasheet for the discrete device product using the graphic design system file; and using a second interface generated by a computing device to provide access to the graphic design system file, the package bonding diagram, the product datasheet, and the product SPICE model.

Implementations disclosed herein may include receiving from a user a selection of at least one die, a package type, and at least one test condition; generating, using a processor, a product die configuration and a product package configuration using a predictive modeling module and the at least one die and the package type; generating a graphic design system file; generating a package bonding diagram; generating a product spice model of the discrete device product using a technology computer aided design module; generating, using a processor, one or more datasheet characteristics of the discrete device product with the product SPICE model; generating a product datasheet for the discrete device product using the graphic design system file; and using a second interface generated by a computing device to provide access to the graphic design system file, the package bonding diagram, the product datasheet, and the product SPICE model.

A method in certain embodiments includes using a computer system that includes an EDA tool to generate a layout of an IC device; searching, using a statistical method such as Bayesian optimization process, for one or more input variable parameters, such as the dimensions of the IC device and the dimensions of the voltage areas in the IC device, that results in an optimal characteristic, such as power, performance or area (PPA) of the IC device, subject to a limiting condition, such as one determined using a cost function. A computer system including one or more EDAs configured to perform the method is also disclosed.