Originally, I was having issues with Ubuntu Server 22.04 installing Cuda and drivers for my two RTX 3090s. After removing one GPU, I was able to get everything installed and working - including running the Cuda bandwidthTest.
I believe the issues I had with the second GPU were related to a bad connection with the riser cable - but I haven’t yet confirmed it.
After installing and configuring the first GPU, I got the second 3090 card now recognized in Ubuntu, however, when running lshw -c display
, it shows the adapter as UNCLAIMED and not using the installed nvidia driver.
*-display:0
description: VGA compatible controller
product: GA102 [GeForce RTX 3090]
vendor: NVIDIA Corporation
physical id: 0
bus info: pci@0000:03:00.0
version: a1
width: 64 bits
clock: 33MHz
capabilities: pm msi pciexpress vga_controller bus_master cap_list
configuration: driver=nvidia latency=0
resources: irq:52 memory:fc000000-fcffffff memory:c0000000-cfffffff memory:d2000000-d3ffffff ioport:d80(size=128)
*-display:1 UNCLAIMED
description: VGA compatible controller
product: GA102 [GeForce RTX 3090]
vendor: NVIDIA Corporation
physical id: 46
bus info: pci@0000:03:02.0
version: a1
width: 64 bits
clock: 33MHz
capabilities: pm msi pciexpress vga_controller cap_list
configuration: latency=0
resources: memory:fb000000-fbffffff memory:b0000000-bfffffff memory:d0000000-d1ffffff ioport:d00(size=128)
Please forgive my lack of experience and knowledge working with Linux. Is there an easy remedy for this?
root@k8dp01:~# cat /proc/driver/nvidia/version
NVRM version: NVIDIA UNIX Open Kernel Module for x86_64 550.54.15 Release Build (dvs-builder@U16-A24-23-2) Tue Mar 5 22:15:33 UTC 2024
GCC version: gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04)