Tessellation apparatus and method

Patent metadata

Field	Value
Publication number	US-10163258-B2
Application number	US-201514795083-A
Country	US
Kind code	B2
Filing date	Jul 9, 2015
Priority date	Jan 6, 2015
Publication date	Dec 25, 2018
Grant date	Dec 25, 2018

Abstract

A tessellation method and apparatus are provided, where the tessellation method includes receiving a first value that is calculated in performing tessellation, the first value being a first floating-point real number represented by a first exponent and a first mantissa; determining a second precision of the first mantissa on the basis of a value of the first exponent and a first precision; and adjusting the first mantissa to have the second precision.

First claim

What is claimed is:

1. A method for performing a tessellation operation in a three-dimensional (3D) graphics processing by a graphics processing system comprising:
obtaining, at a processor, input primitives of a three dimensional (3D) scene;
generating, at the processor, output primitives by performing a tessellation operation on the input primitives; and
generating image pixels based on the output primitives,
the tessellation operation including,
obtaining, at the processor, a first value that is calculated in performing tessellation, the first value being a first floating-point real number represented by a first exponent and a first mantissa,
determining, at the processor, a second precision of the first mantissa based on a value of the first exponent and a first precision,
adjusting, at the processor, the first mantissa to have the second precision,
receiving, at the processor, a tessellation parameter as a second floating-point real number represented by a second exponent and a second mantissa,
determining, at the processor, a fourth precision of the second mantissa based on a value of the second exponent and a third precision, and
adjusting, at the processor, the second mantissa such to have the fourth precision,
wherein the first value comprises a value calculated based on a second floating-point real number having the adjusted second mantissa.

2. The method of claim 1 , wherein the adjusting of the first mantissa comprises rounding off a number of a decimal place such that the first mantissa has the second precision.

3. The method of claim 1 , further comprising receiving a tessellation factor, and the first precision being determined based on the tessellation factor.

4. The method of claim 3 , wherein
a value of the first precision is determined as the first value in response to a value of the tessellation factor being greater than or equal to a preset value, and
the value of the first precision is determined as a second value smaller than the first value in response to the value of the tessellation factor being smaller than the preset value.

5. The method of claim 4 , wherein the first precision increases as the value thereof increases.

6. The method of claim 1 , further comprising calculating barycentric coordinates based on of the second floating-point real number having the adjusted second mantissa, and
wherein the first value comprises the barycentric coordinates.

7. The method of claim 6 , further comprising generating a vertex by calculating a patch equation using the barycentric coordinates, and
wherein the first value comprises a value of the generated vertex.

8. The method of claim 1 , wherein the first precision is predetermined.

9. A non-transitory computer-readable recording medium that stores a program that performs the method of claim 1 when executed by a computer.

10. A graphics processing system for performing a tessellation operation in a three-dimensional (3D) graphics processing comprising:
a memory storing computer-executable instructions; and
one or more processors configured to execute the computer-executable instructions such that the one or more processors are configured to:
obtain input primitives of a three dimensional (3D) scene;
generate output primitives by performing a tessellation operation on the input primitives; and
generate image pixels based on the output primitives,
the performance of the tessellation operation including,
receipt of a first value that is calculated in performing tessellation, the first value being a first floating-point real number represented by a first exponent and a first mantissa,
determination of a second precision of the first mantissa based on a value of the first exponent and a first precision,
adjustment of the first mantissa to have the second precision,
receipt of a tessellation parameter as a second floating-point real number represented by a second exponent and a second mantissa,
determination of a fourth precision of the second mantissa based on a value of the second exponent and a third precision, and
adjustment of the second mantissa to have the fourth precision,
wherein the first value comprises a value calculated based on a second floating-point real number having the adjusted second mantissa.

11. The graphics processing system of claim 10 , wherein the one or more processors are configured to execute the computer-executable instructions such that the one or more processors are further configured to round off a number of a decimal place such that the first mantissa has the second precision.

12. The graphics processing system of claim 10 , wherein the one or more processors are configured to execute the computer-executable instructions such that the one or more processors are further configured to determine the first precision based on a tessellation factor.

13. The graphics processing system of claim 12 , wherein the one or more processors are configured to execute the computer-executable instructions such that the one or more processors are further configured to:
determine a value of the first precision as the first value, in response to a value of the tessellation factor being greater than or equal to a preset value, and
determine the value of the first precision as a second value smaller than the first value, in response to the value of the tessellation factor being smaller than the preset value.

14. The graphics processing system of claim 10 , further comprising a calculator configured to calculate barycentric coordinates based on the second floating-point real number having the adjusted second mantissa, and
wherein the first value comprises the barycentric coordinates.

15. The graphics processing system of claim 14 , wherein:
the calculator is further configured to generate a vertex by calculating a patch equation using the barycentric coordinates, and
the first value comprises a value of the generated vertex.

16. The graphics processing system of claim 10 , wherein the first precision is predetermined.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Park Jeongsoo
• Kwon Kwontaek
• Lee Wonjong

Classifications

• G06T17/20 Primary

  Finite element generation, e.g. wire-frame surface description, {tesselation} · CPC title