diff options
| -rw-r--r-- | README | 32 | ||||
| -rw-r--r-- | setup_enviroment | 27 | ||||
| -rw-r--r-- | src/cuda-sim/cuda-sim.cc | 2 |
3 files changed, 41 insertions, 20 deletions
@@ -1,7 +1,7 @@ -GPGPU-Sim Simulator version 3.0.0b (beta) +GPGPU-Sim Simulator Version 3.0 (beta) This version of GPGPU-Sim works with CUDA version 3.1 and some earlier -versions. It does not work with CUDA version 4.x. +versions. It does not (yet) work with CUDA version 4.x. Please see the copyright notice in the file COPYRIGHT distributed with this release in the same directory as this file. @@ -13,15 +13,18 @@ Analyzing CUDA Workloads Using a Detailed GPU Simulator, in IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), Boston, MA, April 19-21, 2009. -Please sign up for the google groups page for Q&A (see gpgpu-sim.org). +Please sign up for the google groups page for Q&A (see gpgpu-sim.org), but +note that use of this simulator does not imply any level of support. Questions +answered on a best effort basis. See Section 2 "INSTALLING, BUILDING and RUNNING GPGPU-Sim" below to get started. 1. CONTRIBUTIONS and HISTORY -GPGPU-Sim was created at the University of British Columbia by Tor M. Aamodt, -Wilson W. L. Fung, Ali Bakhoda, George Yuan along with contributions by Ivan -Sham, Henry Wong, Henry Tran, and others. +GPGPU-Sim was created by Tor Aamodt's research group at the University of +British Columbia. Many students have contributed including: Wilson W.L. Fung, +Ali Bakhoda, George Yuan, Ivan Sham, Henry Wong, Henry Tran, Andrew Turner, +Aaron Ariel, Inderpret Singh, Tim Rogers, and others. GPGPU-Sim models the features of a modern graphics processor that are relevant to non-graphics applications. The first version of GPGPU-Sim was used in a @@ -59,14 +62,14 @@ Step 2: Download and install the CUDA Toolkit and CUDA SDK code samples from NVIDIA's website: <http://www.nvidia.com/cuda>. 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 install scripts. +LD_LIBRARY_PATH as indicated by the NVIDIA install scripts. -Step 3: Build libcutil.a. The install script for the CUDA SDK does not do this -step automatically. If you installed the CUDA Toolkit in a nonstandard location -you will first need to set CUDA_INSTALL_PATH to the location you installed the -CUDA toolkit (including the trailing "/cuda"). Then, change to the C/common -subdirectory of your CUDA SDK installation (or common subdirectory on older -CUDA SDK versions) and type "make". +Step 3: Build the NVIDIA SDK libcutil.a. The install script for the CUDA SDK +does not do this step automatically. If you installed the CUDA Toolkit in a +nonstandard location you will first need to set CUDA_INSTALL_PATH to the +location you installed the CUDA toolkit (including the trailing "/cuda"). +Then, change to the C/common subdirectory of your CUDA SDK installation (or +common subdirectory on older CUDA SDK versions) and type "make". Step 4: Set environment variables by sourcing the setup_environment script. From a bash shell, type the following in this directory: @@ -93,7 +96,8 @@ necessary). The resulting PTX can be saved to disk by adding -save_embedded_ptx to your gpgpusim.config file (embedded PTX files with be saved as _0.ptx, _1.ptx, etc...). -3. USING THE SIMULATOR +3. USING/MODIFYING THE SIMULATOR Note that doc/GPGPU-Sim_Manual.html has not yet been updated to reflect changes to GPGPU-Sim versus the earlier 2.x versions. + diff --git a/setup_enviroment b/setup_enviroment index c7e30aa..94f9d10 100644 --- a/setup_enviroment +++ b/setup_enviroment @@ -1,5 +1,8 @@ +# see README before running this + +# 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 "$BASH_SOURCE" )" && pwd )" @@ -9,15 +12,29 @@ export BOOST_LIB=/usr/lib64 export BOOST_VER= export NVOPENCL_LIBDIR=/usr/lib64 +# change the following to point to your installation of CUDA Toolkit export CUDA_INSTALL_PATH=$HOME/nvcuda/3.1/cuda export CUDAHOME=$HOME/nvcuda/3.1/cuda + +# change these to point to your installation of the CUDA SDK +# (you also need to build the SDK, see README) export NVIDIA_COMPUTE_SDK_LOCATION=$HOME/NVIDIA_GPU_Computing_SDK/ export NVIDIA_CUDA_SDK_LOCATION=$NVIDIA_COMPUTE_SDK_LOCATION/ + +# setting LD_LIBRARY_PATH as follows enables GPGPU-Sim to be invoked by +# native CUDA and OpenCL applications. GPGPU-Sim is dynamically linked +# against instead of the CUDA toolkit. This replaces this cumbersome +# static link setup in prior GPGPU-Sim releases. export LD_LIBRARY_PATH=$GPGPUSIM_ROOT/lib/$GPGPUSIM_CONFIG:$LD_LIBRARY_PATH export PATH=$GPGPUSIM_ROOT/bin:$CUDA_INSTALL_PATH/bin:$PATH -HF=`hostname -f` -export OPENCL_REMOTE_GPU_HOST=aamodt-pc05.ece.ubc.ca -if [ $HF = $OPENCL_REMOTE_GPU_HOST ]; then - unset OPENCL_REMOTE_GPU_HOST +# The following sets OPENCL_REMOTE_GPU_HOST which is used by GPGPU-Sim to +# 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 diff --git a/src/cuda-sim/cuda-sim.cc b/src/cuda-sim/cuda-sim.cc index 779d138..0c6f849 100644 --- a/src/cuda-sim/cuda-sim.cc +++ b/src/cuda-sim/cuda-sim.cc @@ -1183,7 +1183,7 @@ kernel_info_t *gpgpu_opencl_ptx_sim_init_grid(class function_info *entry, return result; } -const char *g_gpgpusim_version_string = "3.0.0b (beta)"; +const char *g_gpgpusim_version_string = "3.0.9917 (beta)"; void print_splash() { |