Image morphing to meet desired constraints in geometric patterns

Patent metadata

Field	Value
Publication number	US-2019385300-A1
Application number	US-201916557782-A
Country	US
Kind code	A1
Filing date	Aug 30, 2019
Priority date	Aug 30, 2019
Publication date	Dec 19, 2019
Grant date	—

Abstract

A method includes identifying a first geometric pattern that failed a design rule check, identifying a second geometric pattern that passed the design rule check, morphing the first geometric pattern based on the second geometric pattern to generate a morphed geometric pattern, wherein the morphed geometric pattern passes the design rule check, and replacing the first geometric pattern with the morphed geometric pattern.

First claim

What is claimed is:

1 . At least one machine readable storage medium having instructions stored thereon, the instructions when executed by a machine to cause the machine to:
identify a first geometric pattern that failed a design rule check; identify a second geometric pattern that passed the design rule check; morph the first geometric pattern based on the second geometric pattern to generate a morphed geometric pattern, wherein the morphed geometric pattern passes the design rule check; and replace the first geometric pattern with the morphed geometric pattern.

2 . The at least one medium of claim 1 , the instructions when executed by a machine to cause the machine to:
identify a first plurality of geometric patterns that passed the design rule check; and morph the first geometric pattern into a first plurality of morphed geometric patterns, wherein each of the morphed geometric patterns is based on the first geometric pattern and a respective one of the first plurality of morphed geometric patterns.

3 . The at least one medium of claim 2 , the instructions when executed by a machine to cause the machine to identify the first plurality of geometric patterns from a second plurality of geometric patterns that passed the design rule check based on similarities between the first plurality of geometric patterns and the first geometric pattern.

4 . The at least one medium of claim 3 , wherein the similarities are determined based on a comparison of feature values of a plurality of different types of features of the first geometric pattern with corresponding feature values of each of the first plurality of geometric patterns.

5 . The at least one medium of claim 4 , wherein the plurality of different types of features include at least one of a length of a polygon in the first geometric pattern, a width of a polygon in the first geometric pattern, and an eigen vector of an image of the first geometric pattern.

6 . The at least one medium of claim 2 , the instructions when executed by a machine to cause the machine to identify a subset of the first plurality of morphed geometric patterns to present for a selection, wherein the identification of the subset is based on relative similarities between the first geometric pattern and each of the first plurality of morphed geometric patterns.

7 . The at least one medium of claim 6 , the instructions when executed by a machine to cause the machine to replace the first geometric pattern with the morphed geometric pattern responsive to the selection, wherein the selection chooses the morphed geometric pattern from among the subset of the first plurality of morphed geometric patterns.

8 . The at least one medium of claim 6 , the instructions when executed by a machine to cause the machine to update a machine learning model based on the selection, wherein the machine learning model tracks user preferences for particular types of feature changes.

9 . The at least one medium of claim 8 , the instructions when executed by a machine to cause the machine to utilize the machine learning model to identify the first plurality of geometric patterns that passed the design rule check.

10 . The at least one medium of claim 1 , wherein the first geometric pattern is a pattern defined by a portion of a layout database file for a semiconductor chip.

11 . A method comprising:
identifying a first geometric pattern that failed a design rule check; identifying a second geometric pattern that passed the design rule check; morphing the first geometric pattern based on the second geometric pattern to generate a morphed geometric pattern, wherein the morphed geometric pattern passes the design rule check; and replacing the first geometric pattern with the morphed geometric pattern.

12 . The method of claim 11 , further comprising:
identifying a first plurality of geometric patterns that passed the design rule check; and morphing the first geometric pattern into a first plurality of morphed geometric patterns, wherein each of the morphed geometric patterns is based on the first geometric pattern and a respective one of the first plurality of morphed geometric patterns.

13 . The method of claim 12 , further comprising identifying the first plurality of geometric patterns from a second plurality of geometric patterns that passed the design rule check based on similarities between the first plurality of geometric patterns and the first geometric pattern.

14 . The method of claim 12 , further comprising identifying a subset of the first plurality of morphed geometric patterns to present for a selection, wherein the identification of the subset is based on relative similarities between the first geometric pattern and each of the first plurality of morphed geometric patterns to the first geometric pattern.

15 . The method of claim 14 , further comprising replacing the first geometric pattern with the morphed geometric pattern responsive to the selection, wherein the selection chooses the morphed geometric pattern from among the subset of the first plurality of morphed geometric patterns.

16 . An apparatus comprising:
a memory to store identifications of geometric patterns that passed a design rule check; and a processor coupled to the memory, the processor to:
identify a first geometric pattern that failed the design rule check;
identify a second geometric pattern that passed the design rule check;
morph the first geometric pattern based on the second geometric pattern to generate a morphed geometric pattern, wherein the morphed geometric pattern passes the design rule check; and
replace the first geometric pattern with the morphed geometric pattern.

17 . The apparatus of claim 16 , the processor to:
identify a first plurality of geometric patterns that passed the design rule check; and morph the first geometric pattern into a first plurality of morphed geometric patterns, wherein each of the morphed geometric patterns is based on the first geometric pattern and a respective one of the first plurality of morphed geometric patterns.

18 . The apparatus of claim 17 , the processor to identify the first plurality of geometric patterns from a second plurality of geometric patterns that passed the design rule check based on similarities between the first plurality of geometric patterns and the first geometric pattern.

19 . The apparatus of claim 17 , the processor to identify a subset of the first plurality of morphed geometric patterns to present for a selection, wherein the identification of the subset is based on relative similarities between the first geometric pattern and each of the first plurality of morphed geometric patterns to the first geometric pattern.

20 . The apparatus of claim 16 , further comprising one or more of a battery communicatively coupled to the processor, a display communicatively coupled to the processor, or a network interface communicatively coupled to the processor.

Assignees

• Intel Corp

Inventors

• Baidya Bikram
• Erten Hale
• Gu Allan
• Swanson John A
• Singh Vivek K
• Kagalwalla Abde Ali Hunaid
• Yang-Flint Mengfei

Classifications

• G06T7/0006 Primary

  using a design-rule based approach · CPC title

• G06T2207/30148

  Semiconductor; IC; Wafer · CPC title

• G06T7/60

  Analysis of geometric attributes · CPC title

• G06N20/00

  Machine learning · CPC title

• G06T3/0093

  Physics · mapped topic