nvidia-smi: no devices found

Accelerated Computing CUDA CUDA Setup and Installation
1

Ubuntu 18.04.02 LTS

Trying to get a 1080Ti recognized by nvidia-smi, which currently returns “no devices found”. Here are the details:

$ lspci -vvv
    00:05.0 VGA compatible controller: NVIDIA Corporation GP102 [GeForce GTX 1080 Ti] (rev a1) (prog-if 00 [VGA controller])
            Subsystem: eVga.com. Corp. GP102 [GeForce GTX 1080 Ti]
            Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx-
            Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
            Latency: 0
            Interrupt: pin A routed to IRQ 16
            Region 0: Memory at c1000000 (32-bit, non-prefetchable) 
            Region 1: Memory at d000000000 (64-bit, prefetchable) 
            Region 3: Memory at c2000000 (64-bit, prefetchable) 
            Region 5: I/O ports at 2080 
            [virtual] Expansion ROM at 000c0000 [disabled] 
            Capabilities: <access denied>
            Kernel driver in use: nvidia
            Kernel modules: nvidiafb, nouveau, nvidia_drm, nvidia

$ dmesg | grep NVRM
[    4.753635] NVRM: loading NVIDIA UNIX x86_64 Kernel Module  418.56  Fri Mar 15 12:59:26 CDT 2019
[   35.526828] NVRM: RmInitAdapter failed! (0x24:0x65:1070)
[   35.527088] NVRM: rm_init_adapter failed for device bearing minor number 0
[  632.733434] NVRM: RmInitAdapter failed! (0x24:0x65:1070)
[  632.733868] NVRM: rm_init_adapter failed for device bearing minor number 0

$ dmesg | grep nvidia
[    4.616629] nvidia: loading out-of-tree module taints kernel.
[    4.616637] nvidia: module license 'NVIDIA' taints kernel.
[    4.628619] nvidia: module verification failed: signature and/or required key missing - tainting kernel
[    4.649214] nvidia-nvlink: Nvlink Core is being initialized, major device number 241
[    4.649632] nvidia 0000:00:05.0: can't derive routing for PCI INT A
[    4.649634] nvidia 0000:00:05.0: PCI INT A: no GSI
[    4.649743] nvidia 0000:00:05.0: vgaarb: changed VGA decodes: olddecodes=io+mem,decodes=none:owns=io+mem
[    4.766013] nvidia-modeset: Loading NVIDIA Kernel Mode Setting Driver for UNIX platforms  418.56  Fri Mar 15 12:32:40 CDT 2019
[    4.767330] [drm] [nvidia-drm] [GPU ID 0x00000005] Loading driver
[    4.767331] [drm] Initialized nvidia-drm 0.0.0 20160202 for 0000:00:05.0 on minor 0
2

It has been some while but I was under the distinct impression that “nouveau needs to go” when you want to use NVIDIA’s drivers.

3

The nouveau is not loaded, as it does not appear in the lsmod listing. I’m all for somehow removing it out of existence elsewhere. Anyhow, sounds like “signature and/or required key missing” or “can’t derive routing for PCI INT A” is a problem.