I just bought a GeForce GTX 1660 SUPER to explore CUDA programming. I can run some examples but when the card starts working I receive this message (console):
[ 59.970061] resource sanity check: requesting [mem 0x000c0000-0x000fffff], which spans more than PCI Bus 0000:00 [mem 0x000c0000-0x000dffff window]
[ 59.971671] caller _nv000745rm+0x1af/0x200 [nvidia] mapping multiple BARs
It seems the cuda program is able to use the card, but the message is always there. Even if I use the command:
nvidia-smi
My system:
CentOS 8 x64 without GNOME (Just command line)
GeForce GTX 1660 SUPER (6GB)
Driver: NVIDIA-Linux-x86_64-450.66.run
CUDA Version: cuda-repo-rhel8-11-0-local-11.0.3_450.51.06-1.x86_64.rpm
Mother board: TUF B450M-PLUS GAMING
RAM: 16GB
I tried updating CentOS, update the mother board bios, last driver for the card, but there is no solution for that message. I read some threads but there is not solution.
If someone knows how to fix it please let us know.