# US 2024/0202859 A1 · Apparatus and method for a framework for gpu-driven data loading

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

- Number: US 2024/0202859 A1
- Document ID: US20240202859A1
- Status: Published application
- Kind: A1
- Application number: 18/085,367
- Filed: 2022-12-20
- Published: 2024-06-20
- Earliest claimed: 2022-12-20
- Assignees: Tencent America LLC
- Applicants: Tencent America LLC
- Inventors: Minmin GONG
- Web page: https://patentgrep.com/patent/US20240202859A1

## CPC

- G06T 1/20: Processor architectures; Processor configuration, e.g. pipelining
- G06T 1/60: Memory management
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method is provided for data loading at a computing device. The method includes identifying, at a graphics processing unit (GPU), data to load based on execution of an application program. The method also includes loading, via the GPU, data chunks of the identified data in encoded form from a data storage device to a video memory associated with the GPU. The method further includes decoding the data in parallel by using plural GPU thread groups in parallel to decode the data chunks, wherein each of the data chunks is decoded independently of other data chunks.

## Claims

### Claim 1

A method of data loading at a computing device, comprising:
identifying, at a graphics processing unit (GPU), data to load based on execution of an application program;
loading, via the GPU, data chunks of the identified data in encoded form from a data storage device to a video memory associated with the GPU; and
decoding the data chunks in parallel by using plural GPU thread groups in parallel to decode the data chunks, wherein each of the data chunks is decoded independently of other data chunks.

### Claim 2 (depends on 1)

The method of claim 1, wherein each of the plural GPU thread groups decodes a respective one of the data chunks independently of other data chunks by employing in-group decoding functions limited to using data from the respective thread group.

### Claim 3 (depends on 2)

The method of claim 2, wherein decoding the data chunks in parallel includes decoding a first data chunk using a first GPU thread group of the plural GPU thread groups in parallel with and independently from decoding a second data chunk using a second GPU thread group of the plural thread groups.

### Claim 4 (depends on 2)

The method of claim 2, wherein the in-group decoding functions include a shuffle function that allows an inter-thread data exchange within one of the plural GPU thread groups.

### Claim 5 (depends on 2)

The method of claim 2, wherein the in-group decoding functions include a radix sort of one or more threads within one of the plural GPU thread groups, the radix sort having an input bit length that is less than or equal to a number of threads in one of the plural GPU thread groups.

### Claim 6 (depends on 2)

The method of claim 2, wherein the in-group decoding functions include a merge sort applicable to a maximum number of elements equal to a product of a number of elements in one thread and a number of threads in a GPU thread group.

### Claim 7 (depends on 2)

The method of claim 2, wherein the in-group decoding functions include a match operation that includes iteratively (i) copying a non-overlap region split from an overlap region of the data, and (ii) dividing the overlap region into a subsequent non-overlap region and a subsequent overlap region until a length of the subsequent overlap region is less than a distance of the subsequent overlap region.

### Claim 8 (depends on 1)

The method of claim 1, wherein the loading the data to the video memory includes:
mapping a file of the data to a memory block; and
associating the memory block mapped to the file of the data with a buffer using an application program interface (API) extension group.

### Claim 9 (depends on 1)

The method of claim 1, wherein the data corresponds to a video data, texture data, mesh data, neural network data, or text data.

### Claim 10 (depends on 1)

The method of claim 1, further comprising rendering the decoded data for visual representation.

### Claim 11

An apparatus for data loading at a computing device, the apparatus comprising:
a graphics processing unit (GPU) configured to:
identify data to load based on execution of an application program;
load data chunks of the identified data in encoded form from a data storage device to a video memory associated with the GPU; and
decode the data chunks in parallel by using plural GPU thread groups in parallel to decode the data chunks, wherein each of the data chunks is decoded independently of other data chunks.

### Claim 12 (depends on 11)

The apparatus of claim 11, wherein each of the plural GPU thread groups decodes a respective one of the data chunks independently of other data chunks by employing in-group decoding functions limited to using data from the respective thread group.

### Claim 13 (depends on 12)

The apparatus of claim 12, wherein decoding the data chunks in parallel includes decoding a first data chunk using a first GPU thread group of the plural GPU thread groups in parallel with and independently from decoding a second data chunk using a second GPU thread group of the plural thread groups.

### Claim 14 (depends on 12)

The apparatus of claim 12, wherein the in-group decoding functions include a shuffle function that allows an inter-thread data exchange within one of the plural GPU thread groups.

### Claim 15 (depends on 12)

The apparatus of claim 12, wherein the in-group decoding functions include a radix sort of one or more threads within one of the plural GPU thread groups, the radix sort having an input bit length that is less than or equal to a number of threads in one of the plural GPU thread groups.

### Claim 16 (depends on 12)

The apparatus of claim 12, wherein the in-group decoding functions include a merge sort applicable to a maximum number of elements equal to a product of a number of elements in one thread and a number of threads in a GPU thread group.

### Claim 17 (depends on 12)

The apparatus of claim 12, wherein the in-group decoding functions include a match operation that includes iteratively (i) copying a non-overlap region split from an overlap region of the data, and (ii) dividing the overlap region into a subsequent non-overlap region and a subsequent overlap region until a length of the subsequent overlap region is less than a distance of the subsequent overlap region.

### Claim 18 (depends on 11)

The apparatus of claim 11, wherein loading the data to the video memory includes:
mapping a file of the data to a memory block; and
associating the memory block mapped to the file of the data with a buffer using an application program interface (API) extension group.

### Claim 19 (depends on 11)

The apparatus of claim 11, wherein the data corresponds to a video data, texture data, mesh data, neural network data, or text data.

### Claim 20

A non-transitory computer-readable storage medium storing instructions which when executed by at least one processor cause to processor to perform:
identifying, at a graphics processing unit (GPU), data to load based on execution of an application program;
loading, via the GPU, data chunks of the identified data in encoded form from a data storage device to a video memory associated with the GPU; and
decoding the data chunks in parallel by using plural GPU thread groups in parallel to decode the data chunks, wherein each of the data chunks is decoded independently of other data chunks.

### Claim 21

A device, comprising:
a controller configured to:
identify data to load based on execution of an application program;
load data chunks of the identified data in encoded form from a data storage device to a video memory associated with a GPU; and
decode the data chunks in parallel by using plural GPU thread groups in parallel to decode the data chunks, wherein each of the data chunks is decoded independently of other data chunks.

### Claim 22 (depends on 21)

The device of claim 21, wherein each of the plural GPU thread groups decodes a respective one of the data chunks independently of other data chunks by employing in-group decoding functions limited to using data from the respective thread group.

### Claim 23 (depends on 22)

The device of claim 22, wherein decoding the data chunks in parallel includes decoding a first data chunk using a first GPU thread group of the plural GPU thread groups in parallel with and independently from decoding a second data chunk using a second GPU thread group of the plural thread groups.

### Claim 24 (depends on 22)

The device of claim 22, wherein the in-group decoding functions include a shuffle function that allows an inter-thread data exchange within one of the plural GPU thread groups.

### Claim 25 (depends on 22)

The device of claim 22, wherein the in-group decoding functions include a radix sort of one or more threads within one of the plural GPU thread groups, the radix sort having an input bit length that is less than or equal to a number of threads in one of the plural GPU thread groups.

### Claim 26 (depends on 22)

The device of claim 22, wherein the in-group decoding functions include a merge sort applicable to a maximum number of elements equal to a product of a number of elements in one thread and a number of threads in a GPU thread group.

### Claim 27 (depends on 22)

The device of claim 22, wherein the in-group decoding functions include a match operation that includes iteratively (i) copying a non-overlap region split from an overlap region of the data, and (ii) dividing the overlap region into a subsequent non-overlap region and a subsequent overlap region until a length of the subsequent overlap region is less than a distance of the subsequent overlap region.

### Claim 28 (depends on 22)

The device of claim 22, wherein loading the data to the video memory includes:
mapping a file of the data to a memory block; and
associating the memory block mapped to the file of the data with a buffer using an application program interface (API) extension group.

### Claim 29 (depends on 22)

The device of claim 22, wherein the data corresponds to a video data, texture data, mesh data, neural network data, or text data.

### Claim 30 (depends on 21)

The device of claim 21, wherein the controller is further configured to render the decoded data for visual representation.
