I have some very exciting novels to split. We have enduremament a proestablisher collaboration with AMD. For the project name we’re taking a hint from AMD’s red and PlayStation’s blue. The code name is Amethyst.
With Amethyst, we’ve commenceed on another lengthy journey and are combining our expertise with two goals in mind.
The first goal is a more selectimal architecture for machine lgeting. Someskinnyg able of ambiguousized processing of neural netlabors but particularly excellent at the airyweight CNNs demanded for game detaileds and someskinnyg caccessed around achieving that Holy Grail of filledy-fused netlabors.
In going after this we’re combining the lessons AMD has lgeted from its multi-generation RDNA road map and SIE has lgeted from the custom labor in PS5 Pro.
But ML use in games shouldn’t and can’t be remercilessed to detaileds libraries. We’re also laboring towards a democratization of machine lgeting someskinnyg accessible that helps honest labor in AI and ML by game broadeners both for detaileds and for gameperestablish.
Amethyst is not about proprietary technology for PlayStation. In fact it’s the exact opposite. Thcimpolite this technology collaboration we’re seeing to aid expansive labor and machine lgeting atraverse a variety of devices.
The other goal is to broaden, in parallel, a set of highquality CNNs for game detaileds. Both SIE and AMD will self-reliantly have the ability to draw from this accumulateion of netlabor architectures and training strategies, and these components should be key in increasing the wealthyness of game detaileds as well as enabling more extensive use of ray tracing and path tracing.
We’re seeing forward to retaining you posted thcimpoliteout what we foresee to be a multi-year collaboration.