Hi,
I am building a linux box for scientific computing. I plan to use a Tesla K40 for cuda computation, and I was wondering if it is possible to use a geforce card for display? How would I go about doing this? Are the two drivers able to coexist? I would not be doing cuda computation on the display card.
Thanks!
Nathan
You can only use one driver. One NVIDIA driver can support more than one GPU, even of different types.
It is possible to use a GeForce and a Tesla card in the same system.
If the GeForce card is very old (say, before the GeForce GT/GTX 400 series) then you may be limited in what drivers you can use that will support both cards. With a newer GeForce card, just use the latest driver. If you intend to use CUDA, then just load the CUDA toolkit. The driver bundled in it will recognize your GeForce card. Again, if you use CUDA 7, then you will need a GeForce card that is GT/GTX 4xx or newer.
Hi! I have another question. Related to this issue.
Till yesterday I was using Geforce GTX 970 GPU on my Ubuntu 14.04 with CUDA 7 installed.
However today NVDIA’s Tesla K40 GPU donation has arrived.
And I gave away my old Geforce 970.
And instead housed “VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Oland XT [Radeon HD 8670 / R5 340X / R7 250/350X]” GPU as my video output. And Tesla K40 for computing.
Now If I boot ubuntu with both Tesla K40 and video output GPU on board then monitor doesn’t display anything.
If I remove Teska K40 and boot then it is perfectly booting.
I want to use Tesla K40 but I also need different GPU for my display.
How can I solve this issue?
Thanks in advance!
I had the same issue with 2 K40m and a GTX 260, I had to install CUDA, remove nvidia drivers (nvidia-346 for me) and manually install the gtx 260 driver. With lot of luck I guess, all cards worked.
I checked for a Tesla K40 and a GTX 980, the tesla driver states it supports only Tesla cards and Geforce driver (even the latest) doesn’t list the Tesla cards. Is the driver bundled with CUDA special ?