I spent a considerable amount of time getting this to work. None of the tutorials online worked. What I found was so simple….but this had happened a long time ago and I just tried it.
For cuda to work, you have to have the /dev/nvidia* devices. However, just because you have 1 nvidia card doesn’t mean it will always be /dev/nvidia1 So my fix was this:
First Installing Bumblebee Repo + Packages
sudo add-apt-repository ppa:bumblebee/stable
sudo add-apt-repository ppa:ubuntu-x-swat/x-updates
sudo apt-get purge nvidia*
sudo apt-get update
sudo apt-get install bumblebee bumblebee-nvidia linux-headers-genericNext, you will need to blacklist the nouveou module:
sudo sed -i 's/quiet splash/quiet splash nouveau.blacklist=1/g' /etc/default/grubReboot your computer.
After you reboot, you should be able to run optirun glxgears and it should work.
Cuda Package Installation
Go the the nvidia cuda website and download the latest version for ubuntu. When you do the installation, skip the driver installation. Make sure you add the library stuff to the bottom of your .bashrc file:
PATH=$PATH:/usr/local/cuda/bin
LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda/lib64
export PATH
export LD_LIBRARY_PATHAfter it is installed, run the following commands to set up the dev devices properly:
sudo /sbin/rmmod nvidia
sudo mknod -m 666 /dev/nvidia0 c 195 0
sudo mknod -m 666 /dev/nvidiactl c 195 255
sudo mknod -m 666 /dev/nvidia1 c 195 1
sudo /sbin/modprobe nvidiaNow you can compile a cuda app and test your device:
cd /usr/local/cuda/samples/1_Utilities/deviceQuery
sudo make
./deviceQuery./deviceQuery Starting...
CUDA Device Query (Runtime API) version (CUDART static linking)
Detected 1 CUDA Capable device(s)
Device 0: "GeForce GTX 660M"
CUDA Driver Version / Runtime Version 5.0 / 5.0
CUDA Capability Major/Minor version number: 3.0
Total amount of global memory: 2048 MBytes (2147287040 bytes)
( 2) Multiprocessors x (192) CUDA Cores/MP: 384 CUDA Cores
GPU Clock rate: 950 MHz (0.95 GHz)
Memory Clock rate: 2500 Mhz
Memory Bus Width: 128-bit
L2 Cache Size: 262144 bytes
Max Texture Dimension Size (x,y,z) 1D=(65536), 2D=(65536,65536), 3D=(4096,4096,4096)
Max Layered Texture Size (dim) x layers 1D=(16384) x 2048, 2D=(16384,16384) x 2048
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 49152 bytes
Total number of registers available per block: 65536
Warp size: 32
Maximum number of threads per multiprocessor: 2048
Maximum number of threads per block: 1024
Maximum sizes of each dimension of a block: 1024 x 1024 x 64
Maximum sizes of each dimension of a grid: 2147483647 x 65535 x 65535
Maximum memory pitch: 2147483647 bytes
Texture alignment: 512 bytes
Concurrent copy and kernel execution: Yes with 1 copy engine(s)
Run time limit on kernels: No
Integrated GPU sharing Host Memory: No
Support host page-locked memory mapping: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support: Disabled
Device supports Unified Addressing (UVA): Yes
Device PCI Bus ID / PCI location ID: 1 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >
deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 5.0, CUDA Runtime Version = 5.0, NumDevs = 1, Device0 = GeForce GTX 660MOnce cuda is verified as working…..now make sure pyrit can see the device:
$ pyrit list_cores
Pyrit 0.4.1-dev (svn r308) (C) 2008-2011 Lukas Lueg http://pyrit.googlecode.com
This code is distributed under the GNU General Public License v3+
The following cores seem available...
#1: 'CUDA-Device #1 'GeForce GTX 660M''
#2: 'CPU-Core (SSE2/AES)'
#3: 'CPU-Core (SSE2/AES)'
#4: 'CPU-Core (SSE2/AES)'
#5: 'CPU-Core (SSE2/AES)'
#6: 'CPU-Core (SSE2/AES)'
#7: 'CPU-Core (SSE2/AES)'
#8: 'CPU-Core (SSE2/AES)'