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?
DX12 can stack VRAM. Can CUDA? Can Octane?
Forum rules
Please add your OS and Hardware Configuration in your signature, it makes it easier for us to help you analyze problems. Example: Win 7 64 | Geforce GTX680 | i7 3770 | 16GB
Please add your OS and Hardware Configuration in your signature, it makes it easier for us to help you analyze problems. Example: Win 7 64 | Geforce GTX680 | i7 3770 | 16GB
That would imply SLI of some sort. Otherwise it will be worse then out of core.
