My God He recently published a patent for distributing screen load across multiple GPU chips. The game scenario is divided into individual blocks and placed on wooden boards to improve the use of shading in the games. A two-tiered foil container is used for this.
AMD Publishes Patent for GPU Chiplets for Better Use of Shader Technology
A new patent published by AMD opens up more information about what the company plans to do with its next-level GPU and CPU technology in the coming years. In late June, it was revealed that 54 patent applications had been submitted for publication. It is unknown which of the more than fifty published patents will be used in AMD’s plans. The applications discussed in the patents illustrate the company’s approach in subsequent years.
An app that community member @ETI1120 noticed on the website computer basePatent No. US20220207827, discusses critical image data in two stages to efficiently move GPU display loads across multiple chips. This CPU was initially applied to the US Patent Office late last year.
When image data on the GPU is rasterized by standard means, the shader unit, also known as the ALU, performs the similar task and assigns a color name to individual pixels. In contrast, the formatted polygons located in the selected pixel in a given game scene are mapped directly to the pixel. Finally, the formulated task will preserve atypical principles and will differ only in other textures located in different pixels. This method is called SIMD, or Single Instruction – Multiple Data.
For most games today, shaders are not the only task that the GPU has given birth to. But instead, many post-processing elements are added after the initial shading. Actions that the GPU will add, for example, will be the prevention of anti-aliasing, vignetting and blocking in the game environment. However, ray tracing occurs along with shading, creating a new method of computation.
When we talk about the GPU that controls the graphics in today’s games, the load generated by the computer increases exponentially to thousands of compute units.
In gaming on GPUs, this computational load is ideally up to several thousand compute units. This differs from processors in that applications need to be written specifically to add more cores. The CPU scheduler creates this procedure and divides the work of the GPU into more understandable tasks that are processed by computing units, also called binning. The game image is displayed and then divided into separate blocks containing a specified amount of pixels. The block is computed by a graphics processor subunit, where it is synchronized and configured. After this procedure, the pixels that are waiting to be counted are included in a block until the graphics card subunit is finally used. Considerations are made for shading computing power, memory bandwidth, and cache sizes.
AMD states in the patent that partitioning and joining requires a comprehensive and complete data connection between all elements of the GPU, which poses a problem. Data links that are not in the model have a high level of latency, which slows down the process.
CPUs have made this transition to chiplets effortless due to their ability to drive work across multiple cores, making them easy to access chiplets. GPUs do not offer the same flexibility, which makes them comparable to a dual-core processor.
AMD recognizes the need and is trying to provide answers to these issues by changing the rasterization pipeline and sending tasks between multiple GPUs, similar to CPUs. This requires advanced binning technology, which is provided by the company “binning binning”, also known as “binning binning”.
In superassembly, splitting is processed in two separate stages, rather than directly processing in pixel-by-pixel blocks. The first step is to calculate the equation, take a 3D environment and create a 2D image from the original. The stage is called vertex shaders and is completed before rasterization, and the process is very small on the first GPU chip. Once finished, the game scene starts to fade, evolving into jagged tiles and processing on a single GPU chip. After that, routine tasks such as frequency and post-processing can begin.
It is not known when AMD intends to start using this new process or if it will be approved. However, it does give us a glimpse into the future of more efficient GPU processing.
“Friendly zombie fanatic. Analyst. Coffee buff. Professional music specialist. Communicator.”