CUDA stands for Compute Unified Device Architecture. CUDA is a parallel computing architecure and C based programming language for general purpose computing on NVIDIA GPU's
CUDA is currently available on all machines in rooms 325, 215 and 225.
The NVIDIA graphics driver and CUDA compilier are already installed on machines that support CUDA. However, one must set some environment variables in order to run and write CUDA enabled programs.
If you use tcsh, add the following lines to the bottom of your .cshrc file:
# add cuda tools to command path
set path = ( /usr/local/cuda/bin $path )
setenv MANPATH /usr/local/cuda/man:${MANPATH}
# add cuda libraries to library path
if ($?LD_LIBRARY_PATH) then
setenv LD_LIBRARY_PATH /usr/local/cuda/lib64:${LD_LIBRARY_PATH}
else
setenv LD_LIBRARY_PATH /usr/local/cuda/lib64
endif
If you use bash, add the following lines to the bottom of your .bashrc file:
# add cuda tools to command path
export PATH=/usr/local/cuda/bin:${PATH}
export MANPATH=/usr/local/cuda/man:${MANPATH}
# add cuda libraries to library path
if [[ "${LD_LIBRARY_PATH}" != "" ]]
then
export LD_LIBRARY_PATH=/usr/local/cuda/lib64:${LD_LIBRARY_PATH}
else
export LD_LIBRARY_PATH=/usr/local/cuda/lib64
fi
Log out and back in for the changes to take effect.
The cuda SDK has been precompiled in /usr/local/cuda/sdk You are free to browse the demos and look at the source within this tree.
If you would like to install a copy of the SDK into your home directory in order to modify the source code, run the SDK installer:
/usr/local/cuda/sdk/gpucomputingsdk_3.2.16_linux.run
Go go The CUDA Zone