Intel acquired the artificial intelligence company Movidius about 6 years ago. However, since then, no serious action has been taken from Intel in this regard. However, according to the latest information, Intel is working on a new type of processor created to increase the speed of artificial intelligence. No official announcement has been made about the new processor yet, but Intel has recently released a new Linux driver that explicitly references this processor.
Intel plans to accelerate AI operations
The system, called the “Versatile Processing Unit” (VPU), is expected to take place in Intel’s 14th Generation Core (Meteor Lake) processors. According to the claims, the VPU will improve device performance across computer vision and deep learning applications.
Generally speaking, there are two types of AI workloads: training and inference. Training focuses on the use of large-scale datasets to develop AI applications with specific capabilities, while inference feeds these systems with new data to produce a result.
As a product of the amount of data involved, the education side is much more time-consuming due to the high level of computing intensity. By contrast, inference must be completed almost instantly. This makes it clear that computational requirements differ significantly.
While details are obviously scant, Intel’s new VPU appears to be designed to speed up workloads on client devices. It is not yet clear whether the company will benefit from similar technology in other CPU series.
Meteor Lake is expected to be introduced towards the end of 2023. That’s why we won’t be seeing new VPU chips anytime soon. But the presence of the chip offers some additional insight into the broader strategy at Intel. We will see what Intel’s new processor can achieve in the coming years.
So what do you think about this step taken by Intel to accelerate artificial intelligence? You can share your views with us in the comments section.