diff options
| author | Andrew M. B. Boktor <[email protected]> | 2012-04-25 12:39:52 -0800 |
|---|---|---|
| committer | Andrew Boktor <[email protected]> | 2014-08-14 13:19:06 -0700 |
| commit | 54d72b20add6d79c25d97e4963b5c05bb0759e88 (patch) | |
| tree | ff72c66580cff5cc4214253fa1c6b0d8a7aab2a9 | |
| parent | aa6d26d41e88634f0c5143bf87154cef1db06dd7 (diff) | |
Making it clear that we do not need static linking
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12121]
| -rw-r--r-- | README | 12 |
1 files changed, 8 insertions, 4 deletions
@@ -180,11 +180,15 @@ file to "1" (Note: you need CUDA version 4.0 or higher). Now To run a CUDA application on the simulator, simply execute source setup_environment <build_type> - + Use the same <build_type> you used while building the simulator. Then just -launch the executable as you would if it was to run on the hardware. To revert -back to running on the hardware, remove GPGPU-Sim from your LD_LIBRARY_PATH -environment variable. +launch the executable as you would if it was to run on the hardware. By +running "source setup_environment <build_type>" you change your LD_LIBRARY_PATH +to point to GPGPU-Sim's instead of CUDA or OpenCL runtime so that you do NOT +need to re-compile your application simply to run it on GPGPU-Sim. + +To revert back to running on the hardware, remove GPGPU-Sim from your +LD_LIBRARY_PATH environment variable. Running OpenCL applications is identical to running CUDA applications. However, OpenCL applications need to communicate with the NVIDIA driver in order to |