Department of Electrical Engineering and Computer Science



Using CUDA On EECS Systems

Notice: While this page may contain useful information, please be aware that it is out of date. It will be updated soon.

Only a small number of EECS Ubuntu systems have nVidia video cards capable of running CUDA applications. In addition to having an appropriate video card, systems need to run a special video driver. As of this writing, only the Hydra (Min Kao 421) lab systems have been enabled for CUDA.

Is my system enabled for CUDA?

You can check whether the on which you are logged in is enabled for CUDA by running the following command. Note: Make sure to run this from a directory where you have write access, or the command will hang:

#> /usr/local/cuda/sdk/C/bin/linux/release/deviceQuery

On a CUDA-capable system you will receive details about the adapter(s), e.g:

/usr/local/cuda/sdk/C/bin/linux/release/deviceQuery Starting...

CUDA Device Query (Runtime API) version (CUDART static linking)

There is 1 device supporting CUDA

Device 0: "Quadro FX 3800"
  CUDA Driver Version: 3.10
  CUDA Runtime Version: 3.10
  CUDA Capability Major revision number: 1
  CUDA Capability Minor revision number: 3
  Total amount of global memory: 1073414144 bytes
  Number of multiprocessors: 24
  Number of cores: 192
  Total amount of constant memory: 65536 bytes
  Total amount of shared memory per block: 16384 bytes
  Total number of registers available per block: 16384
  Warp size: 32
  Maximum number of threads per block: 512
  Maximum sizes of each dimension of a block: 512 x 512 x 64
  Maximum sizes of each dimension of a grid: 65535 x 65535 x 1
  Maximum memory pitch: 2147483647 bytes
  Texture alignment: 256 bytes
  Clock rate: 1.20 GHz
  Concurrent copy and execution: Yes
  Run time limit on kernels: Yes
  Integrated: No
  Support host page-locked memory mapping: Yes
  Compute mode: Default (multiple host threads can use
  this device simultaneously)
  Concurrent kernel execution: No
  Device has ECC support enabled: No

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 3.10, CUDA Runtime Version =
3.10, NumDevs = 1, Device = Quadro FX 3800

PASSED

If you receive an error such as:

/usr/local/cuda/sdk/C/bin/linux/release/deviceQuery: error while loading shared
libraries: libcudart.so.2: cannot open shared object file:
No such file or directory

or:

CUDA Device Query (Runtime API) version (CUDART static linking)
There is no device supporting CUDA

then your system is not CUDA-enabled.

What version of CUDA is available?

Run the same command as in the previous question and deviceQuery will return versioning information such as:

CUDA Driver Version / Runtime Version 4.0 / 4.0
CUDA Capability Major/Minor version number: 1.3

Will you enable CUDA on my desktop Ubuntu system?

We can install the CUDA-enabled video driver on your system, provided its video card is capable of supporting CUDA. Try to find the manufacturer and model of your video card by running:

#> lspci | grep VGA
01:00.0 VGA compatible controller: nVidia Corporation NV41GL [Quadro FX 1400] (rev a2)

In the above example, the system has a nVidia Quadro FX 1400 video card. Only certain nVidia cards are CUDA-capable. See this website for more information: (new link needed). Enabling the CUDA driver on your system may require a reinstall of the OS.

Where is the CUDA toolkit?

nVidia's CUDA toolkit is available in /usr/local/cuda on all EECS 64-bit Ubuntu 9.04 systems. You will want to add /usr/local/cuda/bin to your shell's PATH variable before attempting CUDA development.

Where is the CUDA SDK?

A copy of the CUDA SDK for Linux has been installed in /usr/local/cuda/SDK. You may still want to use your own copy for development. You can copy or rsync the necessary files to your home area or download the newest SDK from (new link needed). The SDK sample applications are available in /usr/local/cuda/sdk/C/bin/linux/release. Try particles for a GUI CUDA application.

How do I write CUDA applications?

Guides to writing CUDA applications can be found at (new link needed).

CUDA applications crash my X-Windows desktop

Be sure to turn off "Extra" visual effects in the Gnome Appearance Preferences. The compositing window manager can cause problems with CUDA GUI applications. The Appearance Preferences can be found in System → Preferences → Appearance - click on the "Visual Effects" tab.


 

The University of Tennessee, Knoxville. Big Orange. Big Ideas.

Knoxville, Tennessee 37996 | 865-974-1000
The flagship campus of the University of Tennessee System