Showing posts with label OpenCL. Show all posts
Showing posts with label OpenCL. Show all posts

OpenCL

lspci     (GeForce GT 2000 3000 ...   8000   (up 8000 is okay)  ... 100 .....600)hardware supported

CUDA toolkit  -  http://developer.nvidia.com/cuda-downloads
http://www.nvidia.com/content/devzone/index.html
CUDA FOR LINUX
1) Download Toolkit for your system
2) Download Drivers for your system
******************************************************************************

Installing OpenCL on Ubuntu Linux with NVIDIA graphics card

Download the CUDA toolkit for Ubuntu from NVIDIAs CUDA site. Open a terminal an run the installation file with the command:
sudo sh cudatoolkit_3.1_linux_64_ubuntu9.10.run
Download the Developer Drivers for Linux at the same website and install it by first stopping X, running the file and start X again. Do stop X use:
sudo /etc/init.d/gdm stop
(lightdm)
Then get a terminal up by pressing CTRL+ALT+F5, login and navigate to where you downloaded the devdriver then type:
sudo sh devdriver_3.1_linux_64_256.40.run
After the driver has been installed start x again by typing
startx
Before compiling an OpenCL application you need to add the path to the lib folder of CUDA to LD_LIBRARY_PATH like so:
export LD_LIBRARY_PATH=/usr/local/cuda/lib64
******************************************************************************


Reference: http://www.thebigblob.com/getting-started-with-opencl-and-gpu-computing/

http://www.streamcomputing.eu/blog/2011-12-29/opencl-hardware-support/
OpenCL hardware support

http://askubuntu.com/questions/131506/how-can-i-get-nvidia-cuda-or-opencl-working-on-a-laptop-with-nvidia-discrete-car

vim /etc/bash.bashrc


#include
sudo cp -r /usr/include/nvidia-current/CL /usr/include

or 
sudo cp -r /usr/local/cuda/include/CL /usr/include