Michael H Fu

US Patent:

6766500, Jul 20, 2004

Filed:

Dec 6, 2001

Appl. No.:

10/016232

Inventors:

Ross A. Donelly - Sunnyvale CA
William C. Naylor - San Jose CA
Michael Fu - San Jose CA

Assignee:

Synopsys, Inc. - Mountain View CA

International Classification:

G06F 1750

US Classification:

716 10, 716 13, 716 14, 716 12, 716 1

Abstract:

A computer implemented process for the automatic creation of integrated circuit (IC) geometry including a multiple pass process flow using multiple passes of direct timing driven placement after a first pass of non-direct timing driven placement. First, a high level description of the circuit design may be synthesized. Next, a non-direct timing driven placement process may place the design. Then the placed design may be routed. Alternatively, routability may be estimated. After routing, a modified design may be resynthesized. The resynthesized design may then be placed according to a direct timing driven placement process. This sequence may be repeated several times.

US Patent:

20200050965, Feb 13, 2020

Filed:

Aug 7, 2019

Appl. No.:

16/534763

Inventors:

- Albany CA, US
MICHAEL FU - ALBANY CA, US

International Classification:

G06N 20/00
G06N 5/04

Abstract:

A computer-implemented method of performing machine vision prediction of digital images using synthetically generated training assets comprises digitally capturing a plurality of assets; configuring each of the assets in the plurality of assets with a plurality of asset attributes; under computer program control, selecting a plurality of different combinations of parameters from among the plurality of asset attributes, and creating a plurality of sets of different synthetic dataset parameters; using computer graphics software, and example parameter values from among the synthetic dataset parameters, creating a synthetic dataset by compiling from a plurality of example images and metadata; configuring a plurality of machine learning trials and executing the trials to train a machine vision model, resulting in creating and storing a trained machine vision model; executing a validation of the trained machine vision model; and inferring a prediction using the trained machine vision model. Trained models are scored against success criteria and re-trained using pseudo-random sampling of different parameters clustered around failure points. As a result, machine vision models may be trained with high accuracy using large datasets of synthesized digital images that are richly parameterized, rather than human captured digital images.