Hello,
Om UBUNTU 14.04: The Nvidia driver for my K40c ist already installed. xorg.conf is modified.
The driver-setup already made some nvidia-blockdevices in /dev…
The K40c resides on PCI 01:00.1. The Kernelmule is compiled and loaded, nouveau driver is blacklisted and not loaded. But - nvidia-smi reports a communication-error with the GPU.
There is a second small nvidia-GPU (GF6100) and that one is found by nvidia-smi.
What to do now ?
Thanks for reply
lspci | grep -i nv
lsmod | grep -i nouveau
dmesg | grep NVRM
Hello txbob !
Thank you for replying. Here are the results. If the Tesla K40c-card is removed, “nvidia-smi” works without errors (using the small GT610-card). It seems, that the K40C is defektive, but, it worked under Windows and the card is connected to the Power-Supply.
$ nvidia-smi
Unable to determine the device handle for GPU 0000:01:00.0: Unable to communicate with GPU because it is insufficiently powered.
This may be because not all required external power cables are
attached, or the attached cables are not seated properly.
$ lspci | grep -i nv
01:00.0 3D controller: NVIDIA Corporation GK110BGL [Tesla K40c] (rev a1)
02:00.0 VGA compatible controller: NVIDIA Corporation GF119 [GeForce GT 610] (rev a1)
02:00.1 Audio device: NVIDIA Corporation GF119 HDMI Audio Controller (rev a1)
$ lsmod | grep -i nouveau (not loaded)
$ dmesg |grep nvrm
[ 11.388061] NVRM: loading NVIDIA UNIX x86_64 Kernel Module 352.93 Tue Apr 5 18:18:24 PDT 2016
[ 114.654747] NVRM: RmInitAdapter failed! (0x25:0x1c:1372)
[ 114.654764] NVRM: rm_init_adapter failed for device bearing minor number 0
[ 114.654789] NVRM: nvidia_frontend_open: minor 0, module->open() failed, error -5
[ 115.573893] NVRM: Your system is not currently configured to drive a VGA console
[ 115.573897] NVRM: on the primary VGA device. The NVIDIA Linux graphics driver
[ 115.573899] NVRM: requires the use of a text-mode VGA console. Use of other console
[ 115.573900] NVRM: drivers including, but not limited to, vesafb, may result in
[ 115.573901] NVRM: corruption and stability problems, and is not supported.
[ 115.909082] NVRM: RmInitAdapter failed! (0x25:0x1c:1372)
[ 115.909101] NVRM: rm_init_adapter failed for device bearing minor number 0
[ 115.909125] NVRM: nvidia_frontend_open: minor 0, module->open() failed, error -5
[ 441.610831] NVRM: RmInitAdapter failed! (0x25:0x1c:1372)
[ 441.610848] NVRM: rm_init_adapter failed for device bearing minor number 0
[ 441.610885] NVRM: nvidia_frontend_open: minor 0, module->open() failed, error -5
[ 442.441123] NVRM: RmInitAdapter failed! (0x25:0x1c:1372)
[ 442.441139] NVRM: rm_init_adapter failed for device bearing minor number 0
[ 442.441162] NVRM: nvidia_frontend_open: minor 0, module->open() failed, error -5
[ 465.132675] NVRM: RmInitAdapter failed! (0x25:0x1c:1372)
[ 465.132706] NVRM: rm_init_adapter failed for device bearing minor number 0
[ 465.132789] NVRM: nvidia_frontend_open: minor 0, module->open() failed, error -5
[ 465.890546] NVRM: RmInitAdapter failed! (0x25:0x1c:1372)
[ 465.890563] NVRM: rm_init_adapter failed for device bearing minor number 0
[ 465.890585] NVRM: nvidia_frontend_open: minor 0, module->open() failed, error -5
What do you think ?
-K40_user
This suggests that that the K40 is not properly connected to the power supply:
Unable to determine the device handle for GPU 0000:01:00.0: Unable to communicate with GPU because it is insufficiently powered.
This may be because not all required external power cables are
attached, or the attached cables are not seated properly.
Hello txbob,
you are right - it seems like that, but - the card worked properly before (Windows).
Is there any other way to check the funtionality ?
Should i install the CUDApaket ?
greetings
K40_user
Hello txbob !
S O L V E D !!!
Sorry, my stupid mistake. Now, i read the datasheet …
the reason for malfuction was the missing 8-pin ATX-Connector.
I only connected two 6-pin connectors. Thanks to Nvidia,
good papers.
thanks to txbob.
K40_user