IP Library Granted Patent US 10,169,839
Granted Patent B2
US 10,169,839 · App. 15/098,638 · Granted Jan 1, 2019

Method and apparatus for executing graphics pipeline

Inventors: Changmoo Kim (Seoul, KR); Yeongon Cho (Hwaseong-si, KR); Soojung Ryu (Hwaseong-si, KR); Woong Seo (Hwaseong-si, KR)
Assignee: SAMSUNG ELECTRONICS CO., LTD.
G06T1/20G06T1/60G06T15/005G06T2200/28
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,169,839
App. No.
15/098,638
Granted
Jan 1, 2019
Kind
B2
Abstract

A method of executing a graphics pipeline includes calculating, while executing the graphics pipeline on a current frame, a resource for processing properties of an object included in a following frame, determining, based on a result of the calculating, whether to perform a pre-process for the object included in the following frame, performing the pre-processing, when the pre-process is determined to be performed, comprising transforming the properties of the object that are to be processed in a graphics pipeline for the following frame, and executing, when the pre-process is to be performed, the graphics pipeline for the following frame by using the transformed properties of the object.

Claims (29)

1. A method comprising:

executing a graphics pipeline by a graphics processor coupled to a memory, the executing comprising:

while executing the graphics pipeline on a current frame, receiving properties of an object included in a following frame;

determining whether a time benefit is obtainable if a pre-process of the object in the following frame is performed, the time benefit being obtainable when:

N×f ×( Tc/Tr )>1,

where N represents a number of passes in a rendering process when executing the graphics pipeline, f represents usage frequency of the object that is to be pre-processed, T c represents a time taken for a controller to transform a property of the object, and T r represents a time taken for a renderer to transform a property of the object;

performing the pre-process, when it is determined that the time benefit is obtainable, otherwise skipping the pre-process; and

executing, when the pre-process is to be performed, the graphics pipeline for the following frame by using the transformed property of the object.

2. The method of claim 1 , wherein, when the graphics pipeline is a graphics pipeline for tile-based deferred rendering, the pre-process is performed before a pass for tile binning.

3. The method of claim 1 , wherein, when the property of the object relates to a location of the object, the pre-process comprises transforming coordinates of the location.

4. The method of claim 1 , wherein, when the property of the object in the following frame relates to a location of a graphics area allocated in the memory to store the object, the pre-process comprises changing the location of the graphics area allocated in the memory by changing an array order of graphics areas stored in the memory.

5. A non-transitory processor-readable recording medium having recorded thereon coding to control one or more processor devices to implement a method of executing a graphics pipeline, wherein the method comprises:

while executing the graphics pipeline on a current frame, receiving properties of an object included in a following frame;

determining whether a time benefit is obtainable if a pre-process of the object in the following frame is performed, the time benefit being obtainable when:

N×f ×( Tc/Tr )>1,

where N represents a number of passes in a rendering process when executing the graphics pipeline, f represents usage frequency of the object that is to be pre-processed, T c represents a time taken for a controller to transform a property of the object, and T r represents a time taken for a renderer to transform a property of the object;

performing the pre-process, when it is determined that the time benefit is obtainable, otherwise skipping the pre-process; and

executing, when the pre-process is to be performed, the graphics pipeline for the following frame by using the transformed properties of the object.

6. A rendering system comprising:

a memory; and

a graphics processor configured to:

while executing a graphics pipeline on a current frame, receive properties of an object included in a following frame;

determine whether a time benefit is obtainable if a pre-process of the object in the following frame is performed, the time benefit being obtainable when:

N×f ×( Tc/Tr )>1,

where N represents a number of passes in a rendering process when executing the graphics pipeline, f represents usage frequency of the object that is to be pre-processed, T c represents a time taken for a controller to transform a property of the object, and T r represents a time taken for a renderer to transform a property of the object;

perform the pre-process, when it is determined that the time benefit is obtainable, otherwise skip the pre-process; and

execute, when the pre-process is to be performed, the graphics pipeline for the following frame by using the transformed properties of the object.

7. The rendering system of claim 6 , wherein when the property of the object relates to a location of the object, the graphics processor performs a pre-process of transforming coordinates of the location.

8. The rendering system of claim 6 , wherein when the property of the object in the following frame relates to a location of a graphics area allocated in a memory to store the object, the graphics processor performs a pre-process of changing the location of the graphics area allocated in the memory by changing an array order of graphic areas stored in the memory.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 14, 2016
From: KIM, CHANGMOO; CHO, YEONGON; RYU, SOOJUNG; SEO, WOONG
To: SAMSUNG ELECTRONICS CO., LTD.
Reel/Frame 038281/0681 →
Priority Claims (1)
KR 10-2015-0139992 · Oct 5, 2015 · national
Continuity (1)
Related Publication 20170098294A1 · Apr 6, 2017
Cited By (1)
US 12,307,548