diff options
| author | Andrew M. B. Boktor <[email protected]> | 2011-11-09 15:43:50 -0800 |
|---|---|---|
| committer | Andrew Boktor <[email protected]> | 2014-08-14 13:18:24 -0700 |
| commit | 8a7798388b2e7d6b7c162f3f5ac46612d7108b75 (patch) | |
| tree | 059dfdd6ef88b151fe72ae949cdbfce1f3c42367 /setup_environment | |
| parent | 80483f2768a15ed1d8df6a11c60c75882e7622bd (diff) | |
Fixed build fail when there is no opencl
Now, you have to define both NVOPENCL_LIBDIR and NVOPENCL_INCDIR in the setupd_environment script to build with opencl. If any of them is not setup, gpgpu-sim will build will output a warning and built without opencl support.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10873]
Diffstat (limited to 'setup_environment')
| -rw-r--r-- | setup_environment | 17 |
1 files changed, 13 insertions, 4 deletions
diff --git a/setup_environment b/setup_environment index 2d3e59d..a768065 100644 --- a/setup_environment +++ b/setup_environment @@ -2,7 +2,7 @@ # uncomment the line with debug if you want to run GPGPU-Sim in gdb export GPGPUSIM_CONFIG=release -#export GPGPUSIM_CONFIG=debug +# export GPGPUSIM_CONFIG=debug export GPGPUSIM_ROOT="$( cd "$( dirname "$BASH_SOURCE" )" && pwd )" @@ -10,13 +10,22 @@ export QTINC=/usr/include export BOOST_ROOT=/usr/include/boost export BOOST_LIB=/usr/lib64 export BOOST_VER= -export NVOPENCL_LIBDIR=/usr/lib64 + +# change this to point to your opencl library directory, usually /usr/lib +# or /usr/lib64. Not setting this variable will cause gpgpu-sim to build +# without opencl support. +export NVOPENCL_LIBDIR= + +# change this to point to your opencl include directory, usually +# $CUDA_INSTALL_PATH/include. Not setting this variable will cause +# gpgpu-sim to build without opencl support. +export NVOPENCL_INCDIR= # change this to point to your installation of the NVIDIA compute SDK -export NVIDIA_COMPUTE_SDK_LOCATION=~/NVIDIA_GPU_Computing_SDK +export NVIDIA_COMPUTE_SDK_LOCATION=$HOME/NVIDIA_GPU_Computing_SDK/ # change the following to point to your installation of CUDA Toolkit -export CUDA_INSTALL_PATH=$HOME/nvcuda/3.1/cuda +export CUDA_INSTALL_PATH=/usr/local/cuda/ # setting LD_LIBRARY_PATH as follows enables GPGPU-Sim to be invoked by # native CUDA and OpenCL applications. GPGPU-Sim is dynamically linked |
