RTX3090 Trinity Not Detected vs RTX3090 Trinity OC Detected

[mosabe]

Hello, I am currently experiencing a problem,

I have two RTX3090, a Trinity OC and the other Trinity

both on the last drivers 515, Ubuntu 22.04

one working perfectly the other one send errors

lspci | grep NVIDIA
03:00.0 VGA compatible controller: NVIDIA Corporation GA102 [GeForce RTX 3090] (rev a1)
03:00.1 Audio device: NVIDIA Corporation GA102 High Definition Audio Controller (rev a1)
04:00.0 VGA compatible controller: NVIDIA Corporation GA102 [GeForce RTX 3090] (rev ff)   
04:00.1 Audio device: NVIDIA Corporation GA102 High Definition Audio Controller (rev ff)

I looked at the forums but get confused

[generix]

@mosabe

(rev ff)

The gpu is off, fallen off the bus, prbably due to lack of power or overheating.

[mosabe]

I don’t think its the reason.

The power, even if I switch them the problem still there.

Overheating, it not always turn on

It works with Xorg drivers

[generix]

Please run nvidia-bug-report.sh as root and attach the resulting nvidia-bug-report.log.gz file to your post.

[mosabe]

nvidia-bug-report.log.gz (321.4 KB)

[generix]

Like said:

[   11.515007] NVRM: Xid (PCI:0000:0b:00): 79, pid='<unknown>', name=<unknown>, GPU has fallen off the bus.

Please check/swap power connectors, check if it works in another system, if not, it’s broken.

[mosabe]

Well I installed Ubuntu again, I put her alone in the system, I plugged the hdmi directly in the GPU. Without the Nvidia driver.

Like always Asus motherboard in the beginning shows that the pci it detected green.

It worked untill the desktop, 5 seconds later black screen.

I can acces only by ssh.

The fan turn all the times non stop.

[mosabe]

Can it be because of thermo pad change ? We used 3 mm?

Error when closing nvidia-modeset error:

[mosabe]

The problem is Fix, it doesn’t work with 3mm thermopad. Need less. Zotac

Thank you for your help.