PowerColor uses NPUs to lower GPU power consumption and improve frame rates in games

PowerColor has come up with an interesting use for neural processing units (NPUs) in modern CPUs. At Computex 2024, it displayed so-called "Edge AI" technology that pairs a graphics card with an NPU to lower power consumption in games.

The thing works by linking an AMD graphics card with a neural processing unit via "PowerColor GUI," resulting in rather impressive efficiency gains. The manufacturer claims Edge AI managed to lower power consumption in Cyberpunk 2077 from 263W to 205W, which is a 22% improvement. In Final Fantasy XV, the result was also impressive at 18%.

But it is not just energy efficiency, something hardcore PC gamers often dismiss as irrelevant when you need to push frame rates to the very limits. Visitors confirmed that the use of an NPU by PowerColor's software increased frame rates by 10% when compared to a "dumb" system without a neural processing unit.

Although graphics cards remain the most interesting part of modern computers, neural processing units are becoming a new norm. Moreover, Intel, AMD, and especially Qualcomm are betting big on their NPUs to offload various tasks from graphics cards and standard CPU cores. Such tasks enable new experiences and make existing ones much more efficient.

Microsoft is already putting NPUs to some good use with its AutoSR upscaling tech. It recently published a detailed blog post on how the technology can improve the gaming experience. For now, AutoSR is only available on Copilot+ PCs with Qualcomm's new Snapdragon processors, but with Intel and AMD making traditional desktop chips with NPUs, expect these fancy technologies to propagate to regular desktop computers, not just laptops and tablets that, due to their form factor, are not very good at gaming.

It will be very interesting to see how and if PowerColor plans to implement the use of NPUs in its graphics cards. AMD already has neural processing units in its Ryzen 8000 chips, and the upcoming Ryzen AI 300 Series will also feature dedicated hardware for AI tasks, and the same goes for Intel too.