Invention Grant
- Patent Title: Layout parasitics and device parameter prediction using graph neural networks
-
Application No.: US16859585Application Date: 2020-04-27
-
Publication No.: US11651194B2Publication Date: 2023-05-16
- Inventor: Haoxing Ren , George Kokai , Ting Ku , Walker Joseph Turner
- Applicant: NVIDIA Corp.
- Applicant Address: US CA Santa Clara
- Assignee: NVIDIA Corp.
- Current Assignee: NVIDIA Corp.
- Current Assignee Address: US CA Santa Clara
- Agency: Rowan TELS LLC
- Main IPC: G06F16/901
- IPC: G06F16/901 ; G06F17/16 ; G06N3/045
Abstract:
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.
Public/Granted literature
- US20210158127A1 LAYOUT PARASITICS AND DEVICE PARAMETER PREDICTION USING GRAPH NEURAL NETWORKS Public/Granted day:2021-05-27
Information query
