# US 2024/0193720 A1 · Graphics processing systems

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

- Number: US 2024/0193720 A1
- Document ID: US20240193720A1
- Status: Published application
- Kind: A1
- Application number: 18/517,213
- Filed: 2023-11-22
- Published: 2024-06-13
- Earliest claimed: 2022-12-12
- Assignees: Arm Limited
- Applicants: Arm Limited
- Inventors: Rafal Stepuch
- Web page: https://patentgrep.com/patent/US20240193720A1

## CPC

- G06T 1/20: Processor architectures; Processor configuration, e.g. pipelining
- G06T 1/60: Memory management
- G06T 11/40: Filling planar surfaces by adding surface attributes, e.g. adding colours or textures
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A graphics processing system in which a render output is sub-divided into a plurality of tiles for rendering. The graphics processing system includes a memory system, a tiling circuit and a primitive list preparation circuit. The tiling circuit determines which primitives are to be rendered for regions into which the render output is sub-divided. The regions form a plurality of rows and columns of regions. The primitive list preparation circuit prepares and stores primitive lists for regions of the render output identifying the primitives that are to be rendered for the regions. The primitive list preparation circuit also stores a groups of pointers, each group pointing to respective primitive lists. The regions of the render output corresponding to the primitive lists that are pointed to by the pointers of the group of pointers comprise adjacent regions spanning a plurality of rows and a plurality of columns of regions.

## Claims

### Claim 1

A method of processing data in a graphics processing system in which a render output is sub-divided into a plurality of tiles for rendering, the method comprising:
determining which primitives in a sequence of primitives to be processed for the render output are to be rendered for respective regions into which the render output is sub-divided for sorting the primitives, wherein the regions form a plurality of rows and columns of regions;
preparing corresponding primitive lists for respective regions of the render output, each primitive list identifying a respective list of primitives that are to be rendered for the region of the render output to which the primitive list relates;
storing the primitive lists in a first region of a memory system of the graphics processing system;
for each of one or more groups of pointers, each group of pointers comprising a plurality of pointers that point to respective primitive lists:
storing the group of pointers in a second region of the memory system;
wherein the regions of the render output corresponding to the primitive lists that are pointed to by the pointers of the group of pointers comprise adjacent regions spanning a plurality of rows and a plurality of columns of regions.

### Claim 2 (depends on 1)

The method as claimed in claim 1, wherein the method comprises:
for each of a plurality groups of pointers, each group of pointers comprising a plurality of pointers that point to respective primitive lists:
storing the group of pointers in a second region of the memory system;
wherein the regions of the render output corresponding to the primitive lists that are pointed to by the pointers of the group of pointers comprise adjacent regions spanning a plurality of rows and a plurality of columns of regions; and
wherein the plurality of groups of regions of the render output corresponding to the plurality groups of pointers tessellate with each other over the render output.

### Claim 3 (depends on 1)

The method as claimed in claim 1, wherein each group of the groups of regions forms a contiguous block of regions in the render output.

### Claim 4 (depends on 1)

The method as claimed in claim 1, wherein each of the groups of regions is arranged such that the regions of a group of regions do not extend from the end of one row or rows of regions to the beginning of another row or rows of regions.

### Claim 5 (depends on 1)

The method as claimed in claim 1, wherein the method comprises:
for each of the one or more groups of pointers:
storing the group of pointers in a block of data in the second region of the memory system;
wherein the block of data corresponds to a single memory read.

### Claim 6 (depends on 1)

The method as claimed in claim 1, wherein the method comprises:
sub-dividing the render output into a plurality of regions each of a first size for sorting the primitives; and
sub-dividing the render output into a plurality of regions each of a second size for sorting the primitives;
wherein the plurality of regions of a second size each correspond to a plurality of the regions of a first size.

### Claim 7 (depends on 1)

The method as claimed in claim 1, wherein the method comprises:
for each of the one or more groups of pointers:
wherein the regions of the render output corresponding to the primitive lists that are pointed to by the pointers of the group of pointers comprise:
a plurality of adjacent regions of a first size spanning a plurality of rows and a plurality of columns of regions; and
one or more regions of a second size each corresponding to a set of plural adjacent regions of the plurality of adjacent regions of a first size.

### Claim 8 (depends on 1)

The method as claimed in claim 1, wherein the method comprises:
for each of the one or more groups of pointers:
storing further data fields with the group of pointers in the second region of the memory system.

### Claim 9 (depends on 1)

The method as claimed in claim 1, wherein the memory system comprises a cache system and the second region comprises a region of the cache system;
wherein the method comprises:
for each of the one or more groups of pointers:
storing a cache tag in the memory system for the group of pointers.

### Claim 10 (depends on 9)

The method as claimed in claim 9, wherein the cache tag comprises an indication of the position of the regions in the group of regions corresponding to the group of pointers.

### Claim 11

A graphics processing system in which a render output is sub-divided into a plurality of tiles for rendering, the graphics processing system comprising:
a memory system;
a tiling circuit that is operable to perform tiling operations to determine which primitives in a sequence of primitives to be processed for the render output are to be rendered for respective regions into which the render output is sub-divided for sorting the primitives, wherein the regions form a plurality of rows and columns of regions; and
a primitive list preparation circuit that is operable to:
prepare corresponding primitive lists for respective regions of the render output, each primitive list identifying a respective list of primitives that are to be rendered for the region of the render output to which the primitive list relates;
store the primitive lists in a first region of a memory system of the graphics processing system; and
for each of one or more groups of pointers, each group of pointers comprising a plurality of pointers that point to respective primitive lists:
store the group of pointers in a second region of the memory system;
wherein the regions of the render output corresponding to the primitive lists that are pointed to by the pointers of the group of pointers comprise adjacent regions spanning a plurality of rows and a plurality of columns of regions.

### Claim 12 (depends on 11)

The graphics processing system as claimed in claim 11, wherein the primitive list preparation circuit is operable to:
for each of a plurality groups of pointers, each group of pointers comprising a plurality of pointers that point to respective primitive lists:
store the group of pointers in a second region of the memory system;
wherein the regions of the render output corresponding to the primitive lists that are pointed to by the pointers of the group of pointers comprise adjacent regions spanning a plurality of rows and a plurality of columns of regions; and
wherein the plurality of groups of regions of the render output corresponding to the plurality groups of pointers tessellate with each other over the render output.

### Claim 13 (depends on 11)

The graphics processing system as claimed in claim 11, wherein each group of the groups of regions forms a contiguous block of regions in the render output.

### Claim 14 (depends on 11)

The graphics processing system as claimed in claim 11, wherein each of the groups of regions is arranged such that the regions of a group of regions do not extend from the end of one row or rows of regions to the beginning of another row or rows of regions.

### Claim 15 (depends on 11)

The graphics processing system as claimed in claim 11, wherein the primitive list preparation circuit is operable to:
for each of the one or more groups of pointers:
store the group of pointers in a block of data in the second region of the memory system;
wherein the block of data corresponds to a single memory read.

### Claim 16 (depends on 11)

The graphics processing system as claimed in claim 11, wherein the tiling circuit is operable to:
sub-divide the render output into a plurality of regions each of a first size for sorting the primitives; and
sub-divide the render output into a plurality of regions each of a second size for sorting the primitives;
wherein the plurality of regions of a second size each correspond to a plurality of the regions of a first size.

### Claim 17 (depends on 11)

The graphics processing system as claimed in claim 11, wherein the primitive list preparation circuit is operable to:
for each of the one or more groups of pointers:
wherein the regions of the render output corresponding to the primitive lists that are pointed to by the pointers of the group of pointers comprise:
a plurality of adjacent regions of a first size spanning a plurality of rows and a plurality of columns of regions; and
one or more regions of a second size each corresponding to a set of plural adjacent regions of the plurality of adjacent regions of a first size.

### Claim 18 (depends on 11)

The graphics processing system as claimed in claim 11, wherein the primitive list preparation circuit is operable to:
for each of the one or more groups of pointers:
store further data fields with the group of pointers in the second region of the memory system.

### Claim 19 (depends on 11)

The graphics processing system as claimed in claim 11, wherein the memory system comprises a cache system and the second region comprises a region of the cache system;
wherein the primitive list preparation circuit is operable to:
for each of the one or more groups of pointers:
store a cache tag in the memory system for the group of pointers;
wherein the cache tag comprises an indication of the position of the regions in the group of regions corresponding to the group of pointers.

### Claim 20

A non-transitory computer readable storage medium storing computer software code which when executing on a graphics processor performs a method of operating a graphics processing system in which a render output is sub-divided into a plurality of tiles for rendering, the method comprising:
determining which primitives in a sequence of primitives to be processed for the render output are to be rendered for respective regions into which the render output is sub-divided for sorting the primitives, wherein the regions form a plurality of rows and columns of regions;
preparing corresponding primitive lists for respective regions of the render output, each primitive list identifying a respective list of primitives that are to be rendered for the region of the render output to which the primitive list relates;
storing the primitive lists in a first region of a memory system of the graphics processing system;
for each of one or more groups of pointers, each group of pointers comprising a plurality of pointers that point to respective primitive lists:
storing the group of pointers in a second region of the memory system;
wherein the regions of the render output corresponding to the primitive lists that are pointed to by the pointers of the group of pointers comprise adjacent regions spanning a plurality of rows and a plurality of columns of regions.
