> optimizing the SSD-to-VRAM pipeline in a way that component-built PCs won’t be able to do until several new industry standards are developed, with potentially profound impacts on the way games are designed.
What are the innovations? I'm just seeing gen 4 pci-e paired with some sort of nvram solution (details are sparse). Apologies if I'm missing something spectacular here...
The only really interesting thing is that the console SoCs have decompression offload hardware, so data coming in from the SSD at 4-5GB/s can be unpacked to a 9+GB/s stream of assets, straight into the RAM shared by the CPU and GPU. A desktop PC can easily handle the decompression on the CPU with a combination of higher core counts and higher clock speeds, but then the data still needs to be moved across a PCIe link to the GPU.
The SSDs themselves are nothing special, and there's no clear sign of anything else in the storage stack for either new console being novel. It looks like they're improving storage APIs and maybe using an IOMMU, neither of which requires new industry standards for the PC platform.
When it comes to graphics assets, they've been stored compressed and decompressed by the GPU on the fly pretty much since early versions of DirectX. What is the innovative part here?
They're using lossless compression algorithms that are a lot more complicated than S3 Texture Compression and friends, and work on arbitrary data rather than being appropriate only for textures.
What are the innovations? I'm just seeing gen 4 pci-e paired with some sort of nvram solution (details are sparse). Apologies if I'm missing something spectacular here...