Nvidia Corporation

George Ferenc Kokai

Haoxing Ren

Walker Joseph Turner

Ting Ku

Tezaswi Raja

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.

Layout parasitics and device parameter prediction using graph neural networks

A system and method are provided for regulating a supply voltage of a device. The method includes the steps of determining whether a supply voltage for an analog multiplexor is below a threshold voltage. If the supply voltage for the analog multiplexor is below the threshold voltage, then the method includes the step of shorting the supply voltage to an output of the analog multiplexor. However, if the supply voltage for the analog multiplexor is above or equal to the threshold voltage, then the method includes the step of transmitting at least one input signal coupled to the analog multiplexor to the output of the analog multiplexor. A system configured to implement the method may include a power management integrated circuit configured to generate a supply voltage for a device and a device that includes a self-powered analog multiplexor with voltage sensing bypass switch.

Growing community of inventors

Cupertino, CA, United States of America

George Ferenc Kokai