It is normal that we witness a large number of advances created by the most important companies in the technological sector, and they are the ones who end up deciding what the key aspects will be, for example the new components that can be found for a computer. In this case since Intel They want to propose a new type of architecture for GPU this would allow us to achieve a higher level of performance, as well as energy efficiency, and this because a patent this would reveal what the company’s plans are related to these components.
Being one of the leading technology companies on the market, every year Intel presents a large number of new solutions that offer really interesting changes compared to the technologies we can currently find, although this does not imply that they will all arrive on the market, as we can well imagine. Nevertheless, there are numerous patents that we can find both in this company and in others that also share the same technological challenges, seeking to offer new capabilities to improve the performance and efficiency of each of the components that we can be found in a computer.
From Intel they know where the future of GPUs is
One of the considerations which Intel would consider using in your GPU It is a disaggregated architecture and the company has filed a patent that would offer the possibility of modifying the typical monolithic structure it has to adopt one based on chiplets specialized. In case the brand chooses to adopt a design of this type, we could find a series of very important improvements in the designs of the GPUs, and this implementation would significantly improve all aspects that these components can offer.
The approach to this design involves, as we mentioned, the use of small chipsets which are then interconnected with each other, using the company’s technology to split the GPU design into these components, allowing the manufacturer to adjust each of these chiplets for a specific use. (graphics, AI, etc.). Among other things, this type of architecture stands out for its ability to be much more energy efficient, and the fact that it is divided into individual “fragments” allows them to be activated depending on the use, this is that is, they can be turned off to save energy, which allows us to see that this type of designs is a reference for the future.
Although one of the most curious things that can be found in this type of patent which focuses on the use of chipsets and how individual units are managed in different modes, is quite similar to the one presented by AMD with the same objective, seeking to offer a structure of a multichiplet module. This would imply that both companies have recognized this architectural design as one of the most important segments for GPUs, and we could face a race between the two companies to see which of the two manages to develop it first.
