diff options
| -rw-r--r-- | README | 13 | ||||
| -rw-r--r-- | setup_environment | 13 |
2 files changed, 10 insertions, 16 deletions
@@ -62,13 +62,12 @@ Step 2: Download and install the CUDA Toolkit. If you want to run OpenCL on the simulator, download and install NVIDIA's OpenCL driver from <http://developer.nvidia.com/object/opencl-download.html>. Update your PATH and LD_LIBRARY_PATH as indicated by the NVIDIA install scripts. Note that you will -to use the lib64 directory if you are using a 64bit machine. +need to use the lib64 directory if you are using a 64bit machine. -Step 3: Edit CUDA_INSTALL_PATH in the setup_environment file then set -environment variables by sourcing the setup_environment script. From a bash -shell, type the following in this directory: +Step 3: Read the file setup_environment carefully and change it to match your +system. Then, from a bash shell, type the following in this directory: - . setup_environment + source setup_environment Step 4: Type "make" in this directory. This will build the simulator with optimizations enabled so the simulator runs faster. If you want to run the @@ -76,13 +75,13 @@ simulator in gdb to debug it, then uncomment the line #export GPGPUSIM_CONFIG=debug -in setup_environment and type ". setup_environment" again, then "make" again. +in setup_environment and type "source setup_environment" again, then "make" again. Step 5: Copy or create the configuration files gpgpusim.conf and \ icnt_config_quadro_islip.txt in your working directory. Sample configuration files are provided under gpgpu-sim/v3.x/configs/*/ -Step 6: Build a CUDA appliction with a recent version of CUDA (or an OpenCL +Step 6: Build a CUDA appliction (or an OpenCL application). Step 7: Run the application and the device code should now run on the diff --git a/setup_environment b/setup_environment index d3d56f6..179a363 100644 --- a/setup_environment +++ b/setup_environment @@ -12,11 +12,11 @@ export BOOST_LIB=/usr/lib64 export BOOST_VER= export NVOPENCL_LIBDIR=/usr/lib64 -# change this to point to your installation of the NVIDIA compute SDK -export NVIDIA_COMPUTE_SDK_LOCATION=~/NVIDIA_GPU_Computing_SDK +# change the following to point to your installation of the NVIDIA compute SDK +export NVIDIA_COMPUTE_SDK_LOCATION=~/cuda/sdk/3.1/ # change the following to point to your installation of CUDA Toolkit -export CUDA_INSTALL_PATH=$HOME/nvcuda/3.1/cuda +export CUDA_INSTALL_PATH=~/cuda/toolkit/3.1/ # setting LD_LIBRARY_PATH as follows enables GPGPU-Sim to be invoked by # native CUDA and OpenCL applications. GPGPU-Sim is dynamically linked @@ -29,9 +29,4 @@ export PATH=$GPGPUSIM_ROOT/bin:$CUDA_INSTALL_PATH/bin:$PATH # SSH to remote node to generate PTX for OpenCL kernels when running on # a node that does not have an NVIDIA driver installed. # The remote node should have GPGPU-Sim installed at the same path -if [ `hostname -d` = "ece.ubc.ca" ]; then - export OPENCL_REMOTE_GPU_HOST=aamodt-pc05.ece.ubc.ca - if [ `hostname -f` = $OPENCL_REMOTE_GPU_HOST ]; then - unset OPENCL_REMOTE_GPU_HOST - fi -fi +# export OPENCL_REMOTE_GPU_HOST=host.domain |