AMD and Sony Tease Next-Gen Graphics, Possibly for a PS6

AMD and Sony jointly outlined AMD’s approach to improving the performance of its future graphics hardware in a video posted to YouTube this week: compression, aggregation, and dedication. Compress all graphics pipeline data to reduce memory overhead, aggregate compute units that process data for faster matrix multiplication (key to improve AI performance, including scaling) and finally the addition of dedicated silicon to handle the acceleration of ray and path tracing, necessary to improve visual quality.

Sony’s involvement immediately embarrassed everyone PlayStation 6 Rumor: AMD’s chips power Sony’s PlayStation consoles, and that’s about the only place the two companies cross paths, at least for now.

Don’t miss any of our unbiased technical content and lab reviews. Add CNET as your preferred Google source.

AMD powers almost every console, from Xbox At Steam bridgewith the Nintendo Switch line one of the rare exceptions (it is based on Nvidia chips). It is also in laptops and the company’s own graphics cards. If you want gaming on a laptop that won’t blow your budgetbetter integrated graphics are always in your best interest.

The three new technologies presented in the AMD video are:

Radiation cores: My testing over the years has shown that AMD has long lagged behind Nvidia when it comes to ray tracing performance (which isn’t just about pretty highlights – it improves lighting significantly), and that’s at least partly because its processing takes place in its main compute unit cores, which are optimized for processing other types of graphics. Ray tracing therefore significantly slows down your frame rates. And the one-core, one-unit ray tracing architecture limits the amount of processing you can put into it to improve it. The Radiance Cores handle ray tracing acceleration separately, similar to Nvidia’s RT cores.

Neural network: Matrix multiplication is the key algorithm for accelerating on-device AI processing – that’s what Tensor cores handle, for example – and these days, scaling is driven by AI and machine learning-based algorithms, like Nvidia’s DLSS and Intel’s XeSS. Upscaling is important because it is a major way to run higher resolutions without hurting performance, and in many ways it is at the center of a suite of technologies aimed at improving image fidelity and performance. AMD’s version is FidelityFX Super Resolution, and its next generation of technology, FSR Redstone (likely part of RDNA 5), will need these bays, as well as Sony’s variant, PSSR.

Universal Compression: The less compressed your data is, the more memory it requires to process and the slower it moves through a pipeline. Traditionally, GPUs were happy to compress only the biggest memory hogs, starting with textures, in part because putting them into the processing pipeline came with a performance cost. But silicon is so much faster than before that it probably makes sense to use it for all graphics data, which is how universal compression works. Even if performance is poor, that likely means less memory is needed, an important factor for 4K and above gaming as well as pricing.

This teaser is likely the first of millions regarding the new technologies of the PS6 and AMD’s RDNA 5, and I would expect to hear a lot more at CES in January 2026, if not sooner. I contacted AMD for more details, but did not immediately receive a response.