DX12 can stack VRAM. Can CUDA? Can Octane?
Posted: Thu Apr 02, 2015 7:40 pm
This is one of the stunning news of DX12. not just all the other things like using CPUs better for parallelization, but that DX12 (and with it, the cards drivers) can stack VRAM ... so three cards with 3 GB each actually provide 9 GB of VRAM, and no longer just 3x 3GB of the same content.
I wonder what this means for the CUDA apps? Does anyone know, if this also applies to CUDA and maybe then, Octane?
I wonder what this means for the CUDA apps? Does anyone know, if this also applies to CUDA and maybe then, Octane?