A 32-bit application cannot use 64-bit libraries. You would need to get the source code of the game, replace 32-bit PhysX with 64-bit, and recompile it (among other steps). Doing this with code derived from decompilation instead of the original source code might theoretically be possible but I...
Sure. Strix Halo mini-PCs and Macs with LPDDR5(X) can run LLMs just fine. Dedicating the slower pool specifically for AI doesn't really make sense though - if the pool is small it won't be enough, and if the pool is large developers that aren't using AI will want to use that memory for CPU tasks.
32GB memory is the minimum for a console to support running LLMs and other game logic AI models. Whether Sony and Microsoft actually want that ability remains to be seen. In regards to AI for graphics, upscaling decreases VRAM usage but frame generation increases it. Keeping highly detailed...
The split bounding volumes patent sounds like it has similar goal as Mega Geometry's cluster-level acceleration structures, but I'm not sure if it actually works the same way.
I wonder how id Tech would have evolved if id Tech 5 and later versions were licensed to third parties like their predecessors, or at least if Arkane, Tango Gameworks, and MachineGames collaborated with id Software on developing a common version of id Tech to meet the needs of all four studios...
Microsoft can add new features to DirectX on its own. Adding features to Vulkan requires going through the Khronos Group. DX12 is a clean API focused on Windows PCs and Xbox. Vulkan has to support everything from console to mobile to embedded devices to PCs. PlayStation and Apple have their own...
Even an RX 6600 can handle diffuse RTGI; AMD has already supported it for three generations now. Personally, I've read more comments from Pascal users complaining about Alan Wake 2 and Indiana Jones than RNDA1/Vega users.
Developer interest in SVOGI died when they realized the 8th-gen consoles were too weak to support it and it stayed dead when it was revealed that the 9th-gen consoles had HWRT. It's really that simple. Metro Exodus EE and Indiana Jones proved that even a machine with weak HWRT capability like...
Arc Celestial is going to support OMM, or at least something similar to it.
https://old.chipsandcheese.com/2025/03/19/looking-ahead-at-intels-xe3-gpu-architecture/
One potential application for DXCV is that developers can create their own neural upscaler/denoiser/frame generator instead of...
Something like Half-Life 2 RTX - fully dynamic path traced lighting, PBR materials, crisp textures, good geometric detail, but minimal clutter - released a new game could be interesting. Sometimes less is more, especially if having less props strewn around the environment means that the props...
If next-gen has 3D V-Cache that be fairly exotic compared to anything else AMD has put in a console. There were rumors that the Xbox would have an NPU too. If either console does, it would be interesting to how developers juggle having both an NPU and a GPU with matrix units (and a CPU with...
They probably will, but only once they have enough TOPS to run upscaling, denoising, and frame generation simultaneously. And instead of pursuing MFG at fixed generation factors, I believe AMD should go for Adaptive Frame Generation like Lossless Scaling has, where it always ouputs at screen...
Is it actually delivering lower FPS than the 6900 XT in raster-only titles for you? That would be surprising, because according to benchmarks the 9070 XT beats the 7900 XT in raster, which in turn beats the 6900 XT.