Scientific computing and parallel computing C++23/C++26

Guillaume Piolat first.last at
Sat Jan 15 10:35:29 UTC 2022

On Saturday, 15 January 2022 at 09:03:11 UTC, Nicholas Wilson 
> from what I understand unified memory allows the GPU to access 
> the host RAM with the same pointer. This reduces the total 
> memory consumed by the program, but to get to the GPU the data 
> must still cross the PCI-e.

Exactly. I remember that in 2013 "Unified Memory Access" on 
NVIDIA was underwhelming, performing worse than pinned transfer + 
GPU memory access.

More information about the Digitalmars-d mailing list