# US 2015/0145873 A1 · Image Processing Techniques

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2015/0145873 A1
- Document ID: US20150145873A1
- Status: Published application
- Kind: A1
- Application number: 13/516,781
- Filed: 2009-12-23
- Published: 2015-05-28
- Earliest claimed: 2009-12-23
- Assignees: Intel Corporation
- Inventors: Tomas G. Akenine-Moller; Robert M. Toth; Jon N. Hasselgren; Carl J. Munkberg; Franz P. Clarberg
- Web page: https://patentgrep.com/patent/US20150145873A1

## CPC

- G06T 1/20: Processor architectures; Processor configuration, e.g. pipelining
- G06T 11/40: Filling planar surfaces by adding surface attributes, e.g. adding colours or textures
- G06T 15/005: {General purpose rendering architectures}
- G06T 2210/12: Bounding box
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Techniques are described that can delay or even prevent use of memory to store triangles associated with tiles as well as processing resources associated with vertex shading and binning triangles. The techniques can also provide better load balancing among a set of cores, and hence provide better performance. A bounding volume is generated to represent a geometry group. Culling takes place to determine whether a geometry group is to have triangles rendered. Vertex shading and association of triangles with tiles can be performed across multiple cores in parallel. Processing resources are allocated for rasterizing tiles that have been vertex shaded and binned triangles over tiles that have yet to be vertex shaded and binned triangles. Rasterization of triangles of different tiles can be performed by multiple cores in parallel.

## Claims

### Claim 1

A computer-implemented method comprising:
determining a first bounding volume for a first geometry group;
determining a second bounding volume for a second geometry group during a time span overlapping with determining the first bounding volume;
assigning the first geometry group to one or more geometry group bins based on the first bounding volume;
assigning the second geometry group to one or more geometry group bins based on the second bounding volume during a time span overlapping with the assigning the first bounding volume to one or more geometry group bins;
performing back-end processing on a tile identified as ready for back-end processing; and
performing mid-end processing in response to not identifying a tile ready for back-end processing during a time span overlapping with the performing back-end processing.

### Claim 2 (depends on 1)

The method of claim 1, wherein the steps of determining a second bounding volume for a second geometry group and assigning the first geometry group to one or more geometry group bins based on the first bounding volume overlap in time.

### Claim 3 (depends on 1)

The method of claim 1, wherein any of the determining a first bounding volume and determining a second bounding volume comprise:
applying bounded arithmetic techniques to determine a bounding volume for each geometry group.

### Claim 4 (depends on 1)

The method of claim 1, wherein the performing back-end processing comprises:
selecting a highest priority tile ready for back-end processing using a first core;
performing back-end processing on triangles of the selected tile using the first core;
selecting a highest priority tile ready for back-end processing using a second core; and
performing back-end processing on triangles of the selected tile using the second core, wherein either the selecting using the second core or performing using the second core occur during a time span when the first core selects a tile or performs back-end processing.

### Claim 5 (depends on 4)

The method of claim 4, further comprising:
indicating the back-end processed tile as done in response to completion of back-end processing on triangles and
allowing memory allocated for the bounding volume and triangles of the back-end processed tile to be overwritten.

### Claim 6 (depends on 4)

The method of claim 4, wherein the highest priority tile comprises one of:
a tile with most binned triangles, a tile with most memory usage, and a tile with most overlapping geometry groups or
a tile with least binned triangles, a tile with least memory usage, and a tile with least overlapping geometry groups.

### Claim 7

(canceled)

### Claim 8 (depends on 1)

The method of claim 1, wherein the performing mid-end processing comprises:
selecting a highest priority first tile available for mid-end processing and vertex shading and triangle binning a geometry group associated with the selected first tile and
selecting a highest priority second tile available for mid-end processing and vertex shading and triangle binning a geometry group associated with the selected second tile during a time span overlapping with any of the selecting, vertex shading, and triangle binning the geometry group of the first tile.

### Claim 9 (depends on 8)

The method of claim 8, wherein the first tile and the second tile comprise the same tile.

### Claim 10 (depends on 8)

The method of claim 8, wherein any of the highest priority first tile and second tile comprise one of:
a tile with any geometry group that has not been vertex shaded or triangle binned and with a highest estimated number of triangles or a highest number of overlapping geometry groups or
a tile with any geometry group that has not been vertex shaded or triangle binned and with a lowest estimated number of trian les or a lowest number of overlapping geometry groups.

### Claim 11

(canceled)

### Claim 12 (depends on 8)

The method of claim 8, wherein vertex shading and triangle binning any of the first or second tiles comprises:
selecting an unprocessed geometry group and
vertex shading and triangle binning vertices of the selected unprocessed geometry group.

### Claim 13 (depends on 8)

The method of claim 8, further comprising:
marking the highest priority tile available for mid-end processing as being not available for mid-end processing in response to no unprocessed geometry group being associated with the highest priority tile.

### Claim 14 (depends on 8)

The method of claim 8, further comprising:
marking any tile that has all geometry groups shaded and triangle binned as being ready for back-end processing.

### Claim 15 (depends on 1)

The method of claim 1, further comprising:
culling one or more geometry groups to exclude geometry groups from back-end processing of one or more tiles.

### Claim 16

A system comprising:
a processor having multiple cores;
a wireless interface communicatively coupled to the processor;
a display device communicatively coupled to the processor; and
a memory communicatively coupled to the processor, wherein at least one of the cores is configured to:
determine a first bounding volume for a first geometry group;
determine a second bounding volume for a second geometry group during a time span overlapping with a time span to determine the first bounding volume;
assign the first geometry group to one or more geometry group bins based on the first bounding volume;
store the assignment of the first geometry group into the memory;
assign the second geometry group to one or more geometry group bins based on the second bounding volume during a time span overlapping with a time span to assign the first bounding volume to one or more geometry group bins;
store the assignment of the second geometry group into the memory;
perform back-end processing on a tile identified as ready for back-end processing; and
perform mid-end processing in response to not identifying a tile ready for back-end processing during a time span overlapping with the time span to perform back-end processing.

### Claim 17 (depends on 16)

The system of claim 16, wherein to determine a first bounding volume and to determine a second bounding volume, at least one of the cores is to:
apply bounded arithmetic techniques to determine a bounding volume for each geometry group.

### Claim 18 (depends on 16)

The system of claim 16, wherein to perform back-end processing, at least one of the cores is to:
select a highest priority tile ready for back-end processing and
perform back-end processing on triangles of the selected tile.

### Claim 19 (depends on 18)

The system of claim 18, wherein the highest priority tile comprises one of:
a tile with most binned triangles, a tile with most memory usage, and a tile with most overlapping geometry groups or
a tile with least binned triangles, a tile with least memory usage, and a tile with least overlapping geometry groups.

### Claim 20

(canceled)

### Claim 21 (depends on 16)

The system of claim 16, wherein to perform mid-end processing, at least one of the cores is to:
select a highest priority tile available for mid-end processing and vertex shade and triangle bin a geometry group associated with the selected tile.

### Claim 22 (depends on 21)

The system of claim 21, wherein the highest priority tile available for mid-end processing comprises one of:
a tile with any geometry group that has not been vertex shaded or triangle binned and with a highest estimated number of triangles or overlapping geometry groups.
